Advertisement
Guest User

Untitled

a guest
May 26th, 2025
12
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 338.44 KB | Software | 0 0
  1. slot release: id 50 | task 27194 | stop processing: n_past = 131, truncated = 1
  2. slot print_timing: id 50 | task 27194 |
  3. prompt eval time = 2243.34 ms / 199 tokens ( 11.27 ms per token, 88.71 tokens per second)
  4. eval time = 8538.73 ms / 60 tokens ( 142.31 ms per token, 7.03 tokens per second)
  5. total time = 10782.06 ms / 259 tokens
  6. slot release: id 57 | task 27198 | stop processing: n_past = 130, truncated = 1
  7. slot print_timing: id 57 | task 27198 |
  8. prompt eval time = 1037.84 ms / 199 tokens ( 5.22 ms per token, 191.74 tokens per second)
  9. eval time = 7501.38 ms / 59 tokens ( 127.14 ms per token, 7.87 tokens per second)
  10. total time = 8539.22 ms / 258 tokens
  11. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  12. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  13. slot launch_slot_: id 36 | task 27382 | processing task
  14. slot launch_slot_: id 40 | task 27383 | processing task
  15. slot launch_slot_: id 43 | task 26653 | processing task
  16. slot launch_slot_: id 46 | task 26654 | processing task
  17. slot launch_slot_: id 50 | task 26655 | processing task
  18. slot launch_slot_: id 57 | task 26656 | processing task
  19. slot update_slots: id 36 | task 27382 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  20. slot update_slots: id 36 | task 27382 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  21. slot update_slots: id 36 | task 27382 | kv cache rm [0, end)
  22. slot update_slots: id 36 | task 27382 | prompt processing progress, n_past = 199, n_tokens = 257, progress = 1.000000
  23. slot update_slots: id 36 | task 27382 | prompt done, n_past = 199, n_tokens = 257
  24. slot update_slots: id 40 | task 27383 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  25. slot update_slots: id 40 | task 27383 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  26. slot update_slots: id 40 | task 27383 | kv cache rm [0, end)
  27. slot update_slots: id 40 | task 27383 | prompt processing progress, n_past = 199, n_tokens = 456, progress = 1.000000
  28. slot update_slots: id 40 | task 27383 | prompt done, n_past = 199, n_tokens = 456
  29. slot update_slots: id 43 | task 26653 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  30. slot update_slots: id 43 | task 26653 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  31. slot update_slots: id 43 | task 26653 | kv cache rm [0, end)
  32. slot update_slots: id 43 | task 26653 | prompt processing progress, n_past = 199, n_tokens = 655, progress = 1.000000
  33. slot update_slots: id 43 | task 26653 | prompt done, n_past = 199, n_tokens = 655
  34. slot update_slots: id 46 | task 26654 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  35. slot update_slots: id 46 | task 26654 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  36. slot update_slots: id 46 | task 26654 | kv cache rm [0, end)
  37. slot update_slots: id 46 | task 26654 | prompt processing progress, n_past = 199, n_tokens = 854, progress = 1.000000
  38. slot update_slots: id 46 | task 26654 | prompt done, n_past = 199, n_tokens = 854
  39. slot update_slots: id 50 | task 26655 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  40. slot update_slots: id 50 | task 26655 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  41. slot update_slots: id 50 | task 26655 | kv cache rm [0, end)
  42. slot update_slots: id 50 | task 26655 | prompt processing progress, n_past = 199, n_tokens = 1053, progress = 1.000000
  43. slot update_slots: id 50 | task 26655 | prompt done, n_past = 199, n_tokens = 1053
  44. slot update_slots: id 57 | task 26656 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  45. slot update_slots: id 57 | task 26656 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  46. slot update_slots: id 57 | task 26656 | kv cache rm [0, end)
  47. slot update_slots: id 57 | task 26656 | prompt processing progress, n_past = 199, n_tokens = 1252, progress = 1.000000
  48. slot update_slots: id 57 | task 26656 | prompt done, n_past = 199, n_tokens = 1252
  49. srv params_from_: Chat format: Content-only
  50. srv params_from_: Chat format: Content-only
  51. srv cancel_tasks: cancel task, id_task = 27192
  52. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  53. srv params_from_: Chat format: Content-only
  54. slot release: id 31 | task 26486 | stop processing: n_past = 194, truncated = 1
  55. slot print_timing: id 31 | task 26486 |
  56. prompt eval time = 1696.60 ms / 199 tokens ( 8.53 ms per token, 117.29 tokens per second)
  57. eval time = 24149.39 ms / 123 tokens ( 196.34 ms per token, 5.09 tokens per second)
  58. total time = 25845.99 ms / 322 tokens
  59. slot release: id 51 | task 26611 | stop processing: n_past = 131, truncated = 1
  60. slot print_timing: id 51 | task 26611 |
  61. prompt eval time = 3280.27 ms / 199 tokens ( 16.48 ms per token, 60.67 tokens per second)
  62. eval time = 8780.20 ms / 60 tokens ( 146.34 ms per token, 6.83 tokens per second)
  63. total time = 12060.47 ms / 259 tokens
  64. slot release: id 56 | task 27196 | stop processing: n_past = 131, truncated = 1
  65. slot print_timing: id 56 | task 27196 |
  66. prompt eval time = 1036.79 ms / 199 tokens ( 5.21 ms per token, 191.94 tokens per second)
  67. eval time = 8780.95 ms / 60 tokens ( 146.35 ms per token, 6.83 tokens per second)
  68. total time = 9817.73 ms / 259 tokens
  69. slot release: id 60 | task 26612 | stop processing: n_past = 131, truncated = 1
  70. slot print_timing: id 60 | task 26612 |
  71. prompt eval time = 1038.43 ms / 199 tokens ( 5.22 ms per token, 191.64 tokens per second)
  72. eval time = 8779.57 ms / 60 tokens ( 146.33 ms per token, 6.83 tokens per second)
  73. total time = 9818.00 ms / 259 tokens
  74. slot release: id 61 | task 26613 | stop processing: n_past = 131, truncated = 1
  75. slot print_timing: id 61 | task 26613 |
  76. prompt eval time = 1038.51 ms / 199 tokens ( 5.22 ms per token, 191.62 tokens per second)
  77. eval time = 8779.53 ms / 60 tokens ( 146.33 ms per token, 6.83 tokens per second)
  78. total time = 9818.05 ms / 259 tokens
  79. slot release: id 63 | task 26619 | stop processing: n_past = 131, truncated = 1
  80. slot print_timing: id 63 | task 26619 |
  81. prompt eval time = 1038.68 ms / 199 tokens ( 5.22 ms per token, 191.59 tokens per second)
  82. eval time = 8779.40 ms / 60 tokens ( 146.32 ms per token, 6.83 tokens per second)
  83. total time = 9818.08 ms / 259 tokens
  84. slot release: id 49 | task 27192 | stop processing: n_past = 132, truncated = 1
  85. slot launch_slot_: id 31 | task 27386 | processing task
  86. slot launch_slot_: id 51 | task 27385 | processing task
  87. slot launch_slot_: id 56 | task 27388 | processing task
  88. slot launch_slot_: id 60 | task 26660 | processing task
  89. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  90. slot launch_slot_: id 61 | task 26661 | processing task
  91. slot launch_slot_: id 63 | task 26663 | processing task
  92. slot launch_slot_: id 49 | task 26665 | processing task
  93. slot update_slots: id 31 | task 27386 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  94. slot update_slots: id 31 | task 27386 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  95. slot update_slots: id 31 | task 27386 | kv cache rm [0, end)
  96. slot update_slots: id 31 | task 27386 | prompt processing progress, n_past = 199, n_tokens = 256, progress = 1.000000
  97. slot update_slots: id 31 | task 27386 | prompt done, n_past = 199, n_tokens = 256
  98. slot update_slots: id 49 | task 26665 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  99. slot update_slots: id 49 | task 26665 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  100. slot update_slots: id 49 | task 26665 | kv cache rm [0, end)
  101. slot update_slots: id 49 | task 26665 | prompt processing progress, n_past = 199, n_tokens = 455, progress = 1.000000
  102. slot update_slots: id 49 | task 26665 | prompt done, n_past = 199, n_tokens = 455
  103. slot update_slots: id 51 | task 27385 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  104. slot update_slots: id 51 | task 27385 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  105. slot update_slots: id 51 | task 27385 | kv cache rm [0, end)
  106. slot update_slots: id 51 | task 27385 | prompt processing progress, n_past = 199, n_tokens = 654, progress = 1.000000
  107. slot update_slots: id 51 | task 27385 | prompt done, n_past = 199, n_tokens = 654
  108. slot update_slots: id 56 | task 27388 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  109. slot update_slots: id 56 | task 27388 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  110. slot update_slots: id 56 | task 27388 | kv cache rm [0, end)
  111. slot update_slots: id 56 | task 27388 | prompt processing progress, n_past = 199, n_tokens = 853, progress = 1.000000
  112. slot update_slots: id 56 | task 27388 | prompt done, n_past = 199, n_tokens = 853
  113. slot update_slots: id 60 | task 26660 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  114. slot update_slots: id 60 | task 26660 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  115. slot update_slots: id 60 | task 26660 | kv cache rm [0, end)
  116. slot update_slots: id 60 | task 26660 | prompt processing progress, n_past = 199, n_tokens = 1052, progress = 1.000000
  117. slot update_slots: id 60 | task 26660 | prompt done, n_past = 199, n_tokens = 1052
  118. slot update_slots: id 61 | task 26661 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  119. slot update_slots: id 61 | task 26661 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  120. slot update_slots: id 61 | task 26661 | kv cache rm [0, end)
  121. slot update_slots: id 61 | task 26661 | prompt processing progress, n_past = 199, n_tokens = 1251, progress = 1.000000
  122. slot update_slots: id 61 | task 26661 | prompt done, n_past = 199, n_tokens = 1251
  123. slot update_slots: id 63 | task 26663 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  124. slot update_slots: id 63 | task 26663 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  125. slot update_slots: id 63 | task 26663 | kv cache rm [0, end)
  126. slot update_slots: id 63 | task 26663 | prompt processing progress, n_past = 199, n_tokens = 1450, progress = 1.000000
  127. slot update_slots: id 63 | task 26663 | prompt done, n_past = 199, n_tokens = 1450
  128. srv params_from_: Chat format: Content-only
  129. slot release: id 52 | task 26528 | stop processing: n_past = 194, truncated = 1
  130. slot print_timing: id 52 | task 26528 |
  131. prompt eval time = 2344.41 ms / 1 tokens ( 2344.41 ms per token, 0.43 tokens per second)
  132. eval time = 21578.66 ms / 123 tokens ( 175.44 ms per token, 5.70 tokens per second)
  133. total time = 23923.07 ms / 124 tokens
  134. slot launch_slot_: id 52 | task 27390 | processing task
  135. slot update_slots: id 52 | task 27390 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  136. slot update_slots: id 52 | task 27390 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  137. slot update_slots: id 52 | task 27390 | kv cache rm [0, end)
  138. slot update_slots: id 52 | task 27390 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  139. slot update_slots: id 52 | task 27390 | prompt done, n_past = 199, n_tokens = 262
  140. slot release: id 58 | task 26479 | stop processing: n_past = 195, truncated = 1
  141. slot print_timing: id 58 | task 26479 |
  142. prompt eval time = 2344.51 ms / 199 tokens ( 11.78 ms per token, 84.88 tokens per second)
  143. eval time = 22039.12 ms / 124 tokens ( 177.73 ms per token, 5.63 tokens per second)
  144. total time = 24383.62 ms / 323 tokens
  145. slot launch_slot_: id 58 | task 26677 | processing task
  146. slot update_slots: id 58 | task 26677 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  147. slot update_slots: id 58 | task 26677 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  148. slot update_slots: id 58 | task 26677 | kv cache rm [0, end)
  149. slot update_slots: id 58 | task 26677 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  150. slot update_slots: id 58 | task 26677 | prompt done, n_past = 199, n_tokens = 262
  151. slot release: id 20 | task 26497 | stop processing: n_past = 203, truncated = 1
  152. slot print_timing: id 20 | task 26497 |
  153. prompt eval time = 1696.32 ms / 1 tokens ( 1696.32 ms per token, 0.59 tokens per second)
  154. eval time = 26303.38 ms / 132 tokens ( 199.27 ms per token, 5.02 tokens per second)
  155. total time = 27999.69 ms / 133 tokens
  156. slot release: id 32 | task 26505 | stop processing: n_past = 203, truncated = 1
  157. slot print_timing: id 32 | task 26505 |
  158. prompt eval time = 1696.63 ms / 1 tokens ( 1696.63 ms per token, 0.59 tokens per second)
  159. eval time = 26305.10 ms / 132 tokens ( 199.28 ms per token, 5.02 tokens per second)
  160. total time = 28001.73 ms / 133 tokens
  161. slot release: id 47 | task 26526 | stop processing: n_past = 202, truncated = 1
  162. slot print_timing: id 47 | task 26526 |
  163. prompt eval time = 5188.07 ms / 199 tokens ( 26.07 ms per token, 38.36 tokens per second)
  164. eval time = 22815.74 ms / 131 tokens ( 174.17 ms per token, 5.74 tokens per second)
  165. total time = 28003.81 ms / 330 tokens
  166. slot release: id 53 | task 26536 | stop processing: n_past = 202, truncated = 1
  167. slot print_timing: id 53 | task 26536 |
  168. prompt eval time = 2344.44 ms / 1 tokens ( 2344.44 ms per token, 0.43 tokens per second)
  169. eval time = 22816.78 ms / 131 tokens ( 174.17 ms per token, 5.74 tokens per second)
  170. total time = 25161.22 ms / 132 tokens
  171. slot launch_slot_: id 20 | task 26678 | processing task
  172. slot launch_slot_: id 32 | task 26679 | processing task
  173. slot launch_slot_: id 47 | task 26681 | processing task
  174. slot launch_slot_: id 53 | task 26683 | processing task
  175. slot update_slots: id 20 | task 26678 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  176. slot update_slots: id 20 | task 26678 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  177. slot update_slots: id 20 | task 26678 | kv cache rm [0, end)
  178. slot update_slots: id 20 | task 26678 | prompt processing progress, n_past = 199, n_tokens = 259, progress = 1.000000
  179. slot update_slots: id 20 | task 26678 | prompt done, n_past = 199, n_tokens = 259
  180. slot update_slots: id 32 | task 26679 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  181. slot update_slots: id 32 | task 26679 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  182. slot update_slots: id 32 | task 26679 | kv cache rm [0, end)
  183. slot update_slots: id 32 | task 26679 | prompt processing progress, n_past = 199, n_tokens = 458, progress = 1.000000
  184. slot update_slots: id 32 | task 26679 | prompt done, n_past = 199, n_tokens = 458
  185. slot update_slots: id 47 | task 26681 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  186. slot update_slots: id 47 | task 26681 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  187. slot update_slots: id 47 | task 26681 | kv cache rm [0, end)
  188. slot update_slots: id 47 | task 26681 | prompt processing progress, n_past = 199, n_tokens = 657, progress = 1.000000
  189. slot update_slots: id 47 | task 26681 | prompt done, n_past = 199, n_tokens = 657
  190. slot update_slots: id 53 | task 26683 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  191. slot update_slots: id 53 | task 26683 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  192. slot update_slots: id 53 | task 26683 | kv cache rm [0, end)
  193. slot update_slots: id 53 | task 26683 | prompt processing progress, n_past = 199, n_tokens = 856, progress = 1.000000
  194. slot update_slots: id 53 | task 26683 | prompt done, n_past = 199, n_tokens = 856
  195. slot update_slots: id 24 | task 26621 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  196. slot update_slots: id 4 | task 26622 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  197. slot update_slots: id 8 | task 26623 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  198. slot update_slots: id 55 | task 26624 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  199. slot update_slots: id 59 | task 26625 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  200. slot release: id 4 | task 26622 | stop processing: n_past = 131, truncated = 1
  201. slot print_timing: id 4 | task 26622 |
  202. prompt eval time = 231.84 ms / 199 tokens ( 1.17 ms per token, 858.34 tokens per second)
  203. eval time = 11049.72 ms / 60 tokens ( 184.16 ms per token, 5.43 tokens per second)
  204. total time = 11281.56 ms / 259 tokens
  205. slot launch_slot_: id 4 | task 26685 | processing task
  206. slot update_slots: id 7 | task 26626 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  207. slot update_slots: id 14 | task 26627 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  208. slot update_slots: id 4 | task 26685 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  209. slot update_slots: id 4 | task 26685 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  210. slot update_slots: id 4 | task 26685 | kv cache rm [0, end)
  211. slot update_slots: id 4 | task 26685 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  212. slot update_slots: id 4 | task 26685 | prompt done, n_past = 199, n_tokens = 262
  213. slot release: id 55 | task 26624 | stop processing: n_past = 131, truncated = 1
  214. slot print_timing: id 55 | task 26624 |
  215. prompt eval time = 243.30 ms / 199 tokens ( 1.22 ms per token, 817.91 tokens per second)
  216. eval time = 10981.61 ms / 60 tokens ( 183.03 ms per token, 5.46 tokens per second)
  217. total time = 11224.91 ms / 259 tokens
  218. slot launch_slot_: id 55 | task 26686 | processing task
  219. slot update_slots: id 55 | task 26686 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  220. slot update_slots: id 55 | task 26686 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  221. slot update_slots: id 55 | task 26686 | kv cache rm [0, end)
  222. slot update_slots: id 55 | task 26686 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  223. slot update_slots: id 55 | task 26686 | prompt done, n_past = 199, n_tokens = 262
  224. slot release: id 39 | task 26545 | stop processing: n_past = 172, truncated = 1
  225. slot print_timing: id 39 | task 26545 |
  226. prompt eval time = 746.72 ms / 199 tokens ( 3.75 ms per token, 266.50 tokens per second)
  227. eval time = 21145.67 ms / 101 tokens ( 209.36 ms per token, 4.78 tokens per second)
  228. total time = 21892.39 ms / 300 tokens
  229. slot launch_slot_: id 39 | task 26687 | processing task
  230. slot update_slots: id 39 | task 26687 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  231. slot update_slots: id 39 | task 26687 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  232. slot update_slots: id 39 | task 26687 | kv cache rm [0, end)
  233. slot update_slots: id 39 | task 26687 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  234. slot update_slots: id 39 | task 26687 | prompt done, n_past = 199, n_tokens = 262
  235. slot release: id 7 | task 26626 | stop processing: n_past = 131, truncated = 1
  236. slot print_timing: id 7 | task 26626 |
  237. prompt eval time = 241.90 ms / 199 tokens ( 1.22 ms per token, 822.66 tokens per second)
  238. eval time = 11175.53 ms / 60 tokens ( 186.26 ms per token, 5.37 tokens per second)
  239. total time = 11417.42 ms / 259 tokens
  240. slot release: id 11 | task 26575 | stop processing: n_past = 172, truncated = 1
  241. slot print_timing: id 11 | task 26575 |
  242. prompt eval time = 1891.10 ms / 199 tokens ( 9.50 ms per token, 105.23 tokens per second)
  243. eval time = 19414.38 ms / 101 tokens ( 192.22 ms per token, 5.20 tokens per second)
  244. total time = 21305.48 ms / 300 tokens
  245. slot launch_slot_: id 7 | task 26691 | processing task
  246. slot launch_slot_: id 11 | task 26693 | processing task
  247. slot update_slots: id 7 | task 26691 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  248. slot update_slots: id 7 | task 26691 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  249. slot update_slots: id 7 | task 26691 | kv cache rm [0, end)
  250. slot update_slots: id 7 | task 26691 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  251. slot update_slots: id 7 | task 26691 | prompt done, n_past = 199, n_tokens = 261
  252. slot update_slots: id 11 | task 26693 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  253. slot update_slots: id 11 | task 26693 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  254. slot update_slots: id 11 | task 26693 | kv cache rm [0, end)
  255. slot update_slots: id 11 | task 26693 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  256. slot update_slots: id 11 | task 26693 | prompt done, n_past = 199, n_tokens = 460
  257. slot release: id 28 | task 26594 | stop processing: n_past = 172, truncated = 1
  258. slot print_timing: id 28 | task 26594 |
  259. prompt eval time = 2019.73 ms / 199 tokens ( 10.15 ms per token, 98.53 tokens per second)
  260. eval time = 17650.91 ms / 101 tokens ( 174.76 ms per token, 5.72 tokens per second)
  261. total time = 19670.64 ms / 300 tokens
  262. slot launch_slot_: id 28 | task 26652 | processing task
  263. slot update_slots: id 28 | task 26652 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  264. slot update_slots: id 28 | task 26652 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  265. slot update_slots: id 28 | task 26652 | kv cache rm [0, end)
  266. slot update_slots: id 28 | task 26652 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  267. slot update_slots: id 28 | task 26652 | prompt done, n_past = 199, n_tokens = 262
  268. slot release: id 33 | task 26544 | stop processing: n_past = 176, truncated = 1
  269. slot print_timing: id 33 | task 26544 |
  270. prompt eval time = 746.18 ms / 199 tokens ( 3.75 ms per token, 266.69 tokens per second)
  271. eval time = 22121.90 ms / 105 tokens ( 210.68 ms per token, 4.75 tokens per second)
  272. total time = 22868.08 ms / 304 tokens
  273. slot launch_slot_: id 33 | task 26694 | processing task
  274. slot update_slots: id 33 | task 26694 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  275. slot update_slots: id 33 | task 26694 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  276. slot update_slots: id 33 | task 26694 | kv cache rm [0, end)
  277. slot update_slots: id 33 | task 26694 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  278. slot update_slots: id 33 | task 26694 | prompt done, n_past = 199, n_tokens = 262
  279. slot update_slots: id 9 | task 26628 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  280. slot update_slots: id 30 | task 26629 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  281. slot update_slots: id 41 | task 26630 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  282. slot update_slots: id 0 | task 26632 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  283. slot update_slots: id 1 | task 26633 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  284. slot update_slots: id 2 | task 26638 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  285. slot update_slots: id 6 | task 26605 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  286. slot update_slots: id 12 | task 26639 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  287. slot update_slots: id 13 | task 26640 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  288. slot update_slots: id 26 | task 26641 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  289. slot release: id 9 | task 26628 | stop processing: n_past = 130, truncated = 1
  290. slot print_timing: id 9 | task 26628 |
  291. prompt eval time = 595.47 ms / 199 tokens ( 2.99 ms per token, 334.19 tokens per second)
  292. eval time = 11013.37 ms / 59 tokens ( 186.67 ms per token, 5.36 tokens per second)
  293. total time = 11608.84 ms / 258 tokens
  294. slot release: id 41 | task 26630 | stop processing: n_past = 130, truncated = 1
  295. slot print_timing: id 41 | task 26630 |
  296. prompt eval time = 598.28 ms / 199 tokens ( 3.01 ms per token, 332.62 tokens per second)
  297. eval time = 11017.27 ms / 59 tokens ( 186.73 ms per token, 5.36 tokens per second)
  298. total time = 11615.55 ms / 258 tokens
  299. slot launch_slot_: id 9 | task 26696 | processing task
  300. slot launch_slot_: id 41 | task 26697 | processing task
  301. slot update_slots: id 15 | task 27335 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  302. slot update_slots: id 17 | task 27336 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  303. slot update_slots: id 18 | task 27337 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  304. slot update_slots: id 21 | task 27338 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  305. slot update_slots: id 27 | task 27339 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  306. slot update_slots: id 29 | task 27340 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  307. slot update_slots: id 34 | task 27341 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  308. slot update_slots: id 45 | task 27342 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  309. slot update_slots: id 9 | task 26696 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  310. slot update_slots: id 9 | task 26696 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  311. slot update_slots: id 9 | task 26696 | kv cache rm [0, end)
  312. slot update_slots: id 9 | task 26696 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  313. slot update_slots: id 9 | task 26696 | prompt done, n_past = 199, n_tokens = 261
  314. slot update_slots: id 41 | task 26697 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  315. slot update_slots: id 41 | task 26697 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  316. slot update_slots: id 41 | task 26697 | kv cache rm [0, end)
  317. slot update_slots: id 41 | task 26697 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  318. slot update_slots: id 41 | task 26697 | prompt done, n_past = 199, n_tokens = 460
  319. slot release: id 12 | task 26639 | stop processing: n_past = 130, truncated = 1
  320. slot print_timing: id 12 | task 26639 |
  321. prompt eval time = 1084.13 ms / 199 tokens ( 5.45 ms per token, 183.56 tokens per second)
  322. eval time = 10490.95 ms / 59 tokens ( 177.81 ms per token, 5.62 tokens per second)
  323. total time = 11575.08 ms / 258 tokens
  324. slot launch_slot_: id 12 | task 26698 | processing task
  325. slot update_slots: id 36 | task 27382 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  326. slot update_slots: id 40 | task 27383 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  327. slot update_slots: id 43 | task 26653 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  328. slot update_slots: id 46 | task 26654 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  329. slot update_slots: id 50 | task 26655 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  330. slot update_slots: id 57 | task 26656 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  331. slot update_slots: id 12 | task 26698 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  332. slot update_slots: id 12 | task 26698 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  333. slot update_slots: id 12 | task 26698 | kv cache rm [0, end)
  334. slot update_slots: id 12 | task 26698 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  335. slot update_slots: id 12 | task 26698 | prompt done, n_past = 199, n_tokens = 262
  336. slot release: id 0 | task 26632 | stop processing: n_past = 131, truncated = 1
  337. slot print_timing: id 0 | task 26632 |
  338. prompt eval time = 1083.47 ms / 199 tokens ( 5.44 ms per token, 183.67 tokens per second)
  339. eval time = 11004.40 ms / 60 tokens ( 183.41 ms per token, 5.45 tokens per second)
  340. total time = 12087.86 ms / 259 tokens
  341. slot release: id 1 | task 26633 | stop processing: n_past = 131, truncated = 1
  342. slot print_timing: id 1 | task 26633 |
  343. prompt eval time = 1083.46 ms / 199 tokens ( 5.44 ms per token, 183.67 tokens per second)
  344. eval time = 11004.42 ms / 60 tokens ( 183.41 ms per token, 5.45 tokens per second)
  345. total time = 12087.88 ms / 259 tokens
  346. slot release: id 13 | task 26640 | stop processing: n_past = 131, truncated = 1
  347. slot print_timing: id 13 | task 26640 |
  348. prompt eval time = 1084.12 ms / 199 tokens ( 5.45 ms per token, 183.56 tokens per second)
  349. eval time = 11004.58 ms / 60 tokens ( 183.41 ms per token, 5.45 tokens per second)
  350. total time = 12088.70 ms / 259 tokens
  351. slot release: id 18 | task 27337 | stop processing: n_past = 130, truncated = 1
  352. slot print_timing: id 18 | task 27337 |
  353. prompt eval time = 1152.52 ms / 199 tokens ( 5.79 ms per token, 172.67 tokens per second)
  354. eval time = 9846.38 ms / 59 tokens ( 166.89 ms per token, 5.99 tokens per second)
  355. total time = 10998.90 ms / 258 tokens
  356. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  357. srv params_from_: Chat format: Content-only
  358. slot launch_slot_: id 0 | task 26700 | processing task
  359. slot launch_slot_: id 1 | task 26701 | processing task
  360. slot launch_slot_: id 13 | task 26703 | processing task
  361. slot launch_slot_: id 18 | task 26705 | processing task
  362. slot update_slots: id 31 | task 27386 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  363. slot update_slots: id 49 | task 26665 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  364. slot update_slots: id 51 | task 27385 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  365. slot update_slots: id 56 | task 27388 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  366. slot update_slots: id 60 | task 26660 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  367. slot update_slots: id 61 | task 26661 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  368. slot update_slots: id 63 | task 26663 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  369. slot update_slots: id 0 | task 26700 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  370. slot update_slots: id 0 | task 26700 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  371. slot update_slots: id 0 | task 26700 | kv cache rm [0, end)
  372. slot update_slots: id 0 | task 26700 | prompt processing progress, n_past = 199, n_tokens = 259, progress = 1.000000
  373. slot update_slots: id 0 | task 26700 | prompt done, n_past = 199, n_tokens = 259
  374. slot update_slots: id 1 | task 26701 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  375. slot update_slots: id 1 | task 26701 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  376. slot update_slots: id 1 | task 26701 | kv cache rm [0, end)
  377. slot update_slots: id 1 | task 26701 | prompt processing progress, n_past = 199, n_tokens = 458, progress = 1.000000
  378. slot update_slots: id 1 | task 26701 | prompt done, n_past = 199, n_tokens = 458
  379. slot update_slots: id 13 | task 26703 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  380. slot update_slots: id 13 | task 26703 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  381. slot update_slots: id 13 | task 26703 | kv cache rm [0, end)
  382. slot update_slots: id 13 | task 26703 | prompt processing progress, n_past = 199, n_tokens = 657, progress = 1.000000
  383. slot update_slots: id 13 | task 26703 | prompt done, n_past = 199, n_tokens = 657
  384. slot update_slots: id 18 | task 26705 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  385. slot update_slots: id 18 | task 26705 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  386. slot update_slots: id 18 | task 26705 | kv cache rm [0, end)
  387. slot update_slots: id 18 | task 26705 | prompt processing progress, n_past = 199, n_tokens = 856, progress = 1.000000
  388. slot update_slots: id 18 | task 26705 | prompt done, n_past = 199, n_tokens = 856
  389. slot release: id 15 | task 27335 | stop processing: n_past = 131, truncated = 1
  390. slot print_timing: id 15 | task 27335 |
  391. prompt eval time = 1151.27 ms / 199 tokens ( 5.79 ms per token, 172.85 tokens per second)
  392. eval time = 10588.47 ms / 60 tokens ( 176.47 ms per token, 5.67 tokens per second)
  393. total time = 11739.74 ms / 259 tokens
  394. srv cancel_tasks: cancel task, id_task = 27335
  395. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  396. slot release: id 17 | task 27336 | stop processing: n_past = 131, truncated = 1
  397. slot print_timing: id 17 | task 27336 |
  398. prompt eval time = 1152.33 ms / 199 tokens ( 5.79 ms per token, 172.69 tokens per second)
  399. eval time = 10587.56 ms / 60 tokens ( 176.46 ms per token, 5.67 tokens per second)
  400. total time = 11739.89 ms / 259 tokens
  401. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  402. slot release: id 29 | task 27340 | stop processing: n_past = 131, truncated = 1
  403. slot print_timing: id 29 | task 27340 |
  404. prompt eval time = 1154.84 ms / 199 tokens ( 5.80 ms per token, 172.32 tokens per second)
  405. eval time = 10587.88 ms / 60 tokens ( 176.46 ms per token, 5.67 tokens per second)
  406. total time = 11742.72 ms / 259 tokens
  407. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  408. slot release: id 34 | task 27341 | stop processing: n_past = 131, truncated = 1
  409. slot print_timing: id 34 | task 27341 |
  410. prompt eval time = 1155.73 ms / 199 tokens ( 5.81 ms per token, 172.19 tokens per second)
  411. eval time = 10588.86 ms / 60 tokens ( 176.48 ms per token, 5.67 tokens per second)
  412. total time = 11744.58 ms / 259 tokens
  413. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  414. srv params_from_: Chat format: Content-only
  415. srv params_from_: Chat format: Content-only
  416. srv params_from_: Chat format: Content-only
  417. slot release: id 50 | task 26655 | stop processing: n_past = 130, truncated = 1
  418. slot print_timing: id 50 | task 26655 |
  419. prompt eval time = 1275.57 ms / 199 tokens ( 6.41 ms per token, 156.01 tokens per second)
  420. eval time = 9311.77 ms / 59 tokens ( 157.83 ms per token, 6.34 tokens per second)
  421. total time = 10587.33 ms / 258 tokens
  422. srv params_from_: Chat format: Content-only
  423. slot launch_slot_: id 15 | task 26706 | processing task
  424. slot launch_slot_: id 17 | task 26570 | processing task
  425. slot launch_slot_: id 29 | task 26707 | processing task
  426. slot launch_slot_: id 34 | task 26708 | processing task
  427. slot launch_slot_: id 50 | task 27450 | processing task
  428. slot update_slots: id 52 | task 27390 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  429. slot update_slots: id 15 | task 26706 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  430. slot update_slots: id 15 | task 26706 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  431. slot update_slots: id 15 | task 26706 | kv cache rm [0, end)
  432. slot update_slots: id 15 | task 26706 | prompt processing progress, n_past = 199, n_tokens = 258, progress = 1.000000
  433. slot update_slots: id 15 | task 26706 | prompt done, n_past = 199, n_tokens = 258
  434. slot update_slots: id 17 | task 26570 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  435. slot update_slots: id 17 | task 26570 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  436. slot update_slots: id 17 | task 26570 | kv cache rm [0, end)
  437. slot update_slots: id 17 | task 26570 | prompt processing progress, n_past = 199, n_tokens = 457, progress = 1.000000
  438. slot update_slots: id 17 | task 26570 | prompt done, n_past = 199, n_tokens = 457
  439. slot update_slots: id 29 | task 26707 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  440. slot update_slots: id 29 | task 26707 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  441. slot update_slots: id 29 | task 26707 | kv cache rm [0, end)
  442. slot update_slots: id 29 | task 26707 | prompt processing progress, n_past = 199, n_tokens = 656, progress = 1.000000
  443. slot update_slots: id 29 | task 26707 | prompt done, n_past = 199, n_tokens = 656
  444. slot update_slots: id 34 | task 26708 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  445. slot update_slots: id 34 | task 26708 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  446. slot update_slots: id 34 | task 26708 | kv cache rm [0, end)
  447. slot update_slots: id 34 | task 26708 | prompt processing progress, n_past = 199, n_tokens = 855, progress = 1.000000
  448. slot update_slots: id 34 | task 26708 | prompt done, n_past = 199, n_tokens = 855
  449. slot update_slots: id 50 | task 27450 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  450. slot update_slots: id 50 | task 27450 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  451. slot update_slots: id 50 | task 27450 | kv cache rm [0, end)
  452. slot update_slots: id 50 | task 27450 | prompt processing progress, n_past = 199, n_tokens = 1054, progress = 1.000000
  453. slot update_slots: id 50 | task 27450 | prompt done, n_past = 199, n_tokens = 1054
  454. slot release: id 31 | task 27386 | stop processing: n_past = 130, truncated = 1
  455. slot print_timing: id 31 | task 27386 |
  456. prompt eval time = 909.63 ms / 199 tokens ( 4.57 ms per token, 218.77 tokens per second)
  457. eval time = 9180.13 ms / 59 tokens ( 155.60 ms per token, 6.43 tokens per second)
  458. total time = 10089.77 ms / 258 tokens
  459. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  460. slot release: id 40 | task 27383 | stop processing: n_past = 131, truncated = 1
  461. slot print_timing: id 40 | task 27383 |
  462. prompt eval time = 1273.51 ms / 199 tokens ( 6.40 ms per token, 156.26 tokens per second)
  463. eval time = 10097.20 ms / 60 tokens ( 168.29 ms per token, 5.94 tokens per second)
  464. total time = 11370.71 ms / 259 tokens
  465. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  466. srv cancel_tasks: cancel task, id_task = 27342
  467. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  468. srv params_from_: Chat format: Content-only
  469. srv params_from_: Chat format: Content-only
  470. slot release: id 57 | task 26656 | stop processing: n_past = 131, truncated = 1
  471. slot print_timing: id 57 | task 26656 |
  472. prompt eval time = 1277.18 ms / 199 tokens ( 6.42 ms per token, 155.81 tokens per second)
  473. eval time = 10098.36 ms / 60 tokens ( 168.31 ms per token, 5.94 tokens per second)
  474. total time = 11375.55 ms / 259 tokens
  475. slot release: id 60 | task 26660 | stop processing: n_past = 130, truncated = 1
  476. slot print_timing: id 60 | task 26660 |
  477. prompt eval time = 916.52 ms / 199 tokens ( 4.61 ms per token, 217.12 tokens per second)
  478. eval time = 9180.74 ms / 59 tokens ( 155.61 ms per token, 6.43 tokens per second)
  479. total time = 10097.26 ms / 258 tokens
  480. slot release: id 45 | task 27342 | stop processing: n_past = 132, truncated = 1
  481. slot launch_slot_: id 31 | task 26709 | processing task
  482. slot launch_slot_: id 40 | task 26710 | processing task
  483. slot launch_slot_: id 57 | task 26711 | processing task
  484. slot launch_slot_: id 60 | task 27456 | processing task
  485. slot launch_slot_: id 45 | task 27457 | processing task
  486. slot update_slots: id 58 | task 26677 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  487. slot update_slots: id 31 | task 26709 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  488. slot update_slots: id 31 | task 26709 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  489. slot update_slots: id 31 | task 26709 | kv cache rm [0, end)
  490. slot update_slots: id 31 | task 26709 | prompt processing progress, n_past = 199, n_tokens = 258, progress = 1.000000
  491. slot update_slots: id 31 | task 26709 | prompt done, n_past = 199, n_tokens = 258
  492. slot update_slots: id 40 | task 26710 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  493. slot update_slots: id 40 | task 26710 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  494. slot update_slots: id 40 | task 26710 | kv cache rm [0, end)
  495. slot update_slots: id 40 | task 26710 | prompt processing progress, n_past = 199, n_tokens = 457, progress = 1.000000
  496. slot update_slots: id 40 | task 26710 | prompt done, n_past = 199, n_tokens = 457
  497. slot update_slots: id 45 | task 27457 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  498. slot update_slots: id 45 | task 27457 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  499. slot update_slots: id 45 | task 27457 | kv cache rm [0, end)
  500. slot update_slots: id 45 | task 27457 | prompt processing progress, n_past = 199, n_tokens = 656, progress = 1.000000
  501. slot update_slots: id 45 | task 27457 | prompt done, n_past = 199, n_tokens = 656
  502. slot update_slots: id 57 | task 26711 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  503. slot update_slots: id 57 | task 26711 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  504. slot update_slots: id 57 | task 26711 | kv cache rm [0, end)
  505. slot update_slots: id 57 | task 26711 | prompt processing progress, n_past = 199, n_tokens = 855, progress = 1.000000
  506. slot update_slots: id 57 | task 26711 | prompt done, n_past = 199, n_tokens = 855
  507. slot update_slots: id 60 | task 27456 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  508. slot update_slots: id 60 | task 27456 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  509. slot update_slots: id 60 | task 27456 | kv cache rm [0, end)
  510. slot update_slots: id 60 | task 27456 | prompt processing progress, n_past = 199, n_tokens = 1054, progress = 1.000000
  511. slot update_slots: id 60 | task 27456 | prompt done, n_past = 199, n_tokens = 1054
  512. srv params_from_: Chat format: Content-only
  513. slot release: id 5 | task 26572 | stop processing: n_past = 194, truncated = 1
  514. slot print_timing: id 5 | task 26572 |
  515. prompt eval time = 1890.88 ms / 199 tokens ( 9.50 ms per token, 105.24 tokens per second)
  516. eval time = 24977.55 ms / 123 tokens ( 203.07 ms per token, 4.92 tokens per second)
  517. total time = 26868.43 ms / 322 tokens
  518. slot release: id 49 | task 26665 | stop processing: n_past = 131, truncated = 1
  519. slot print_timing: id 49 | task 26665 |
  520. prompt eval time = 913.93 ms / 199 tokens ( 4.59 ms per token, 217.74 tokens per second)
  521. eval time = 9981.71 ms / 60 tokens ( 166.36 ms per token, 6.01 tokens per second)
  522. total time = 10895.65 ms / 259 tokens
  523. slot release: id 61 | task 26661 | stop processing: n_past = 131, truncated = 1
  524. slot print_timing: id 61 | task 26661 |
  525. prompt eval time = 916.63 ms / 199 tokens ( 4.61 ms per token, 217.10 tokens per second)
  526. eval time = 9981.62 ms / 60 tokens ( 166.36 ms per token, 6.01 tokens per second)
  527. total time = 10898.26 ms / 259 tokens
  528. slot release: id 63 | task 26663 | stop processing: n_past = 131, truncated = 1
  529. slot print_timing: id 63 | task 26663 |
  530. prompt eval time = 916.73 ms / 199 tokens ( 4.61 ms per token, 217.08 tokens per second)
  531. eval time = 9981.92 ms / 60 tokens ( 166.37 ms per token, 6.01 tokens per second)
  532. total time = 10898.65 ms / 259 tokens
  533. slot launch_slot_: id 5 | task 27459 | processing task
  534. slot launch_slot_: id 49 | task 26713 | processing task
  535. slot launch_slot_: id 61 | task 26715 | processing task
  536. slot launch_slot_: id 63 | task 26714 | processing task
  537. slot update_slots: id 5 | task 27459 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  538. slot update_slots: id 5 | task 27459 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  539. slot update_slots: id 5 | task 27459 | kv cache rm [0, end)
  540. slot update_slots: id 5 | task 27459 | prompt processing progress, n_past = 199, n_tokens = 259, progress = 1.000000
  541. slot update_slots: id 5 | task 27459 | prompt done, n_past = 199, n_tokens = 259
  542. slot update_slots: id 49 | task 26713 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  543. slot update_slots: id 49 | task 26713 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  544. slot update_slots: id 49 | task 26713 | kv cache rm [0, end)
  545. slot update_slots: id 49 | task 26713 | prompt processing progress, n_past = 199, n_tokens = 458, progress = 1.000000
  546. slot update_slots: id 49 | task 26713 | prompt done, n_past = 199, n_tokens = 458
  547. slot update_slots: id 61 | task 26715 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  548. slot update_slots: id 61 | task 26715 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  549. slot update_slots: id 61 | task 26715 | kv cache rm [0, end)
  550. slot update_slots: id 61 | task 26715 | prompt processing progress, n_past = 199, n_tokens = 657, progress = 1.000000
  551. slot update_slots: id 61 | task 26715 | prompt done, n_past = 199, n_tokens = 657
  552. slot update_slots: id 63 | task 26714 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  553. slot update_slots: id 63 | task 26714 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  554. slot update_slots: id 63 | task 26714 | kv cache rm [0, end)
  555. slot update_slots: id 63 | task 26714 | prompt processing progress, n_past = 199, n_tokens = 856, progress = 1.000000
  556. slot update_slots: id 63 | task 26714 | prompt done, n_past = 199, n_tokens = 856
  557. srv cancel_tasks: cancel task, id_task = 27338
  558. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  559. srv params_from_: Chat format: Content-only
  560. slot release: id 21 | task 27338 | stop processing: n_past = 134, truncated = 1
  561. slot launch_slot_: id 21 | task 27462 | processing task
  562. slot update_slots: id 19 | task 26483 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  563. slot update_slots: id 22 | task 26488 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  564. slot update_slots: id 23 | task 26535 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  565. slot update_slots: id 25 | task 26512 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  566. slot update_slots: id 35 | task 26522 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  567. slot update_slots: id 37 | task 26484 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  568. slot update_slots: id 21 | task 27462 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  569. slot update_slots: id 21 | task 27462 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  570. slot update_slots: id 21 | task 27462 | kv cache rm [0, end)
  571. slot update_slots: id 21 | task 27462 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  572. slot update_slots: id 21 | task 27462 | prompt done, n_past = 199, n_tokens = 262
  573. slot release: id 58 | task 26677 | stop processing: n_past = 131, truncated = 1
  574. slot print_timing: id 58 | task 26677 |
  575. prompt eval time = 422.19 ms / 199 tokens ( 2.12 ms per token, 471.35 tokens per second)
  576. eval time = 10198.08 ms / 60 tokens ( 169.97 ms per token, 5.88 tokens per second)
  577. total time = 10620.27 ms / 259 tokens
  578. slot launch_slot_: id 58 | task 26719 | processing task
  579. slot update_slots: id 48 | task 26498 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  580. slot update_slots: id 54 | task 26525 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  581. slot update_slots: id 58 | task 26719 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  582. slot update_slots: id 58 | task 26719 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  583. slot update_slots: id 58 | task 26719 | kv cache rm [0, end)
  584. slot update_slots: id 58 | task 26719 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  585. slot update_slots: id 58 | task 26719 | prompt done, n_past = 199, n_tokens = 262
  586. srv cancel_tasks: cancel task, id_task = 27339
  587. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  588. srv params_from_: Chat format: Content-only
  589. slot release: id 27 | task 27339 | stop processing: n_past = 137, truncated = 1
  590. slot launch_slot_: id 27 | task 27467 | processing task
  591. slot update_slots: id 27 | task 27467 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  592. slot update_slots: id 27 | task 27467 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  593. slot update_slots: id 27 | task 27467 | kv cache rm [0, end)
  594. slot update_slots: id 27 | task 27467 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  595. slot update_slots: id 27 | task 27467 | prompt done, n_past = 199, n_tokens = 262
  596. slot update_slots: id 20 | task 26678 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  597. slot update_slots: id 32 | task 26679 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  598. slot update_slots: id 47 | task 26681 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  599. slot update_slots: id 53 | task 26683 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  600. slot release: id 3 | task 26567 | stop processing: n_past = 203, truncated = 1
  601. slot print_timing: id 3 | task 26567 |
  602. prompt eval time = 1890.78 ms / 199 tokens ( 9.50 ms per token, 105.25 tokens per second)
  603. eval time = 27444.28 ms / 132 tokens ( 207.91 ms per token, 4.81 tokens per second)
  604. total time = 29335.06 ms / 331 tokens
  605. slot release: id 10 | task 26576 | stop processing: n_past = 203, truncated = 1
  606. slot print_timing: id 10 | task 26576 |
  607. prompt eval time = 1891.11 ms / 199 tokens ( 9.50 ms per token, 105.23 tokens per second)
  608. eval time = 27445.45 ms / 132 tokens ( 207.92 ms per token, 4.81 tokens per second)
  609. total time = 29336.56 ms / 331 tokens
  610. slot release: id 20 | task 26678 | stop processing: n_past = 131, truncated = 1
  611. slot print_timing: id 20 | task 26678 |
  612. prompt eval time = 432.17 ms / 199 tokens ( 2.17 ms per token, 460.47 tokens per second)
  613. eval time = 10770.12 ms / 60 tokens ( 179.50 ms per token, 5.57 tokens per second)
  614. total time = 11202.29 ms / 259 tokens
  615. slot release: id 32 | task 26679 | stop processing: n_past = 131, truncated = 1
  616. slot print_timing: id 32 | task 26679 |
  617. prompt eval time = 434.98 ms / 199 tokens ( 2.19 ms per token, 457.50 tokens per second)
  618. eval time = 10769.85 ms / 60 tokens ( 179.50 ms per token, 5.57 tokens per second)
  619. total time = 11204.82 ms / 259 tokens
  620. slot release: id 47 | task 26681 | stop processing: n_past = 131, truncated = 1
  621. slot print_timing: id 47 | task 26681 |
  622. prompt eval time = 438.53 ms / 199 tokens ( 2.20 ms per token, 453.79 tokens per second)
  623. eval time = 10769.50 ms / 60 tokens ( 179.49 ms per token, 5.57 tokens per second)
  624. total time = 11208.03 ms / 259 tokens
  625. slot launch_slot_: id 3 | task 26721 | processing task
  626. slot launch_slot_: id 10 | task 26722 | processing task
  627. slot launch_slot_: id 20 | task 26723 | processing task
  628. slot launch_slot_: id 32 | task 26724 | processing task
  629. slot launch_slot_: id 47 | task 26725 | processing task
  630. slot update_slots: id 3 | task 26721 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  631. slot update_slots: id 3 | task 26721 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  632. slot update_slots: id 3 | task 26721 | kv cache rm [0, end)
  633. slot update_slots: id 3 | task 26721 | prompt processing progress, n_past = 199, n_tokens = 258, progress = 1.000000
  634. slot update_slots: id 3 | task 26721 | prompt done, n_past = 199, n_tokens = 258
  635. slot update_slots: id 10 | task 26722 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  636. slot update_slots: id 10 | task 26722 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  637. slot update_slots: id 10 | task 26722 | kv cache rm [0, end)
  638. slot update_slots: id 10 | task 26722 | prompt processing progress, n_past = 199, n_tokens = 457, progress = 1.000000
  639. slot update_slots: id 10 | task 26722 | prompt done, n_past = 199, n_tokens = 457
  640. slot update_slots: id 20 | task 26723 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  641. slot update_slots: id 20 | task 26723 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  642. slot update_slots: id 20 | task 26723 | kv cache rm [0, end)
  643. slot update_slots: id 20 | task 26723 | prompt processing progress, n_past = 199, n_tokens = 656, progress = 1.000000
  644. slot update_slots: id 20 | task 26723 | prompt done, n_past = 199, n_tokens = 656
  645. slot update_slots: id 32 | task 26724 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  646. slot update_slots: id 32 | task 26724 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  647. slot update_slots: id 32 | task 26724 | kv cache rm [0, end)
  648. slot update_slots: id 32 | task 26724 | prompt processing progress, n_past = 199, n_tokens = 855, progress = 1.000000
  649. slot update_slots: id 32 | task 26724 | prompt done, n_past = 199, n_tokens = 855
  650. slot update_slots: id 47 | task 26725 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  651. slot update_slots: id 47 | task 26725 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  652. slot update_slots: id 47 | task 26725 | kv cache rm [0, end)
  653. slot update_slots: id 47 | task 26725 | prompt processing progress, n_past = 199, n_tokens = 1054, progress = 1.000000
  654. slot update_slots: id 47 | task 26725 | prompt done, n_past = 199, n_tokens = 1054
  655. slot release: id 59 | task 26625 | stop processing: n_past = 172, truncated = 1
  656. slot print_timing: id 59 | task 26625 |
  657. prompt eval time = 244.69 ms / 199 tokens ( 1.23 ms per token, 813.28 tokens per second)
  658. eval time = 20624.75 ms / 101 tokens ( 204.21 ms per token, 4.90 tokens per second)
  659. total time = 20869.44 ms / 300 tokens
  660. slot launch_slot_: id 59 | task 26726 | processing task
  661. slot update_slots: id 59 | task 26726 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  662. slot update_slots: id 59 | task 26726 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  663. slot update_slots: id 59 | task 26726 | kv cache rm [0, end)
  664. slot update_slots: id 59 | task 26726 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  665. slot update_slots: id 59 | task 26726 | prompt done, n_past = 199, n_tokens = 262
  666. slot release: id 42 | task 26606 | stop processing: n_past = 214, truncated = 1
  667. slot print_timing: id 42 | task 26606 |
  668. prompt eval time = 2241.95 ms / 199 tokens ( 11.27 ms per token, 88.76 tokens per second)
  669. eval time = 24904.63 ms / 143 tokens ( 174.16 ms per token, 5.74 tokens per second)
  670. total time = 27146.59 ms / 342 tokens
  671. slot launch_slot_: id 42 | task 26727 | processing task
  672. slot update_slots: id 42 | task 26727 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  673. slot update_slots: id 42 | task 26727 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  674. slot update_slots: id 42 | task 26727 | kv cache rm [0, end)
  675. slot update_slots: id 42 | task 26727 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  676. slot update_slots: id 42 | task 26727 | prompt done, n_past = 199, n_tokens = 262
  677. slot update_slots: id 4 | task 26685 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  678. slot update_slots: id 55 | task 26686 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  679. slot release: id 4 | task 26685 | stop processing: n_past = 130, truncated = 1
  680. slot print_timing: id 4 | task 26685 |
  681. prompt eval time = 162.65 ms / 199 tokens ( 0.82 ms per token, 1223.52 tokens per second)
  682. eval time = 11102.70 ms / 59 tokens ( 188.18 ms per token, 5.31 tokens per second)
  683. total time = 11265.34 ms / 258 tokens
  684. slot launch_slot_: id 4 | task 26573 | processing task
  685. slot update_slots: id 39 | task 26687 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  686. slot update_slots: id 4 | task 26573 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  687. slot update_slots: id 4 | task 26573 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  688. slot update_slots: id 4 | task 26573 | kv cache rm [0, end)
  689. slot update_slots: id 4 | task 26573 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  690. slot update_slots: id 4 | task 26573 | prompt done, n_past = 199, n_tokens = 262
  691. slot update_slots: id 7 | task 26691 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  692. slot update_slots: id 11 | task 26693 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  693. slot update_slots: id 28 | task 26652 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  694. slot release: id 7 | task 26691 | stop processing: n_past = 130, truncated = 1
  695. slot print_timing: id 7 | task 26691 |
  696. prompt eval time = 244.22 ms / 199 tokens ( 1.23 ms per token, 814.85 tokens per second)
  697. eval time = 10941.39 ms / 59 tokens ( 185.45 ms per token, 5.39 tokens per second)
  698. total time = 11185.60 ms / 258 tokens
  699. slot release: id 39 | task 26687 | stop processing: n_past = 131, truncated = 1
  700. slot print_timing: id 39 | task 26687 |
  701. prompt eval time = 164.31 ms / 199 tokens ( 0.83 ms per token, 1211.15 tokens per second)
  702. eval time = 11196.96 ms / 60 tokens ( 186.62 ms per token, 5.36 tokens per second)
  703. total time = 11361.27 ms / 259 tokens
  704. slot launch_slot_: id 7 | task 26728 | processing task
  705. slot launch_slot_: id 39 | task 26729 | processing task
  706. slot update_slots: id 7 | task 26728 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  707. slot update_slots: id 7 | task 26728 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  708. slot update_slots: id 7 | task 26728 | kv cache rm [0, end)
  709. slot update_slots: id 7 | task 26728 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  710. slot update_slots: id 7 | task 26728 | prompt done, n_past = 199, n_tokens = 261
  711. slot update_slots: id 39 | task 26729 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  712. slot update_slots: id 39 | task 26729 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  713. slot update_slots: id 39 | task 26729 | kv cache rm [0, end)
  714. slot update_slots: id 39 | task 26729 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  715. slot update_slots: id 39 | task 26729 | prompt done, n_past = 199, n_tokens = 460
  716. slot release: id 11 | task 26693 | stop processing: n_past = 131, truncated = 1
  717. slot print_timing: id 11 | task 26693 |
  718. prompt eval time = 244.47 ms / 199 tokens ( 1.23 ms per token, 814.00 tokens per second)
  719. eval time = 11192.37 ms / 60 tokens ( 186.54 ms per token, 5.36 tokens per second)
  720. total time = 11436.84 ms / 259 tokens
  721. slot launch_slot_: id 11 | task 26732 | processing task
  722. slot update_slots: id 33 | task 26694 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  723. slot update_slots: id 11 | task 26732 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  724. slot update_slots: id 11 | task 26732 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  725. slot update_slots: id 11 | task 26732 | kv cache rm [0, end)
  726. slot update_slots: id 11 | task 26732 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  727. slot update_slots: id 11 | task 26732 | prompt done, n_past = 199, n_tokens = 262
  728. slot release: id 8 | task 26623 | stop processing: n_past = 195, truncated = 1
  729. slot print_timing: id 8 | task 26623 |
  730. prompt eval time = 232.12 ms / 199 tokens ( 1.17 ms per token, 857.33 tokens per second)
  731. eval time = 23508.00 ms / 124 tokens ( 189.58 ms per token, 5.27 tokens per second)
  732. total time = 23740.12 ms / 323 tokens
  733. slot release: id 28 | task 26652 | stop processing: n_past = 131, truncated = 1
  734. slot print_timing: id 28 | task 26652 |
  735. prompt eval time = 167.24 ms / 199 tokens ( 0.84 ms per token, 1189.89 tokens per second)
  736. eval time = 11348.07 ms / 60 tokens ( 189.13 ms per token, 5.29 tokens per second)
  737. total time = 11515.31 ms / 259 tokens
  738. slot launch_slot_: id 8 | task 26734 | processing task
  739. slot launch_slot_: id 28 | task 26735 | processing task
  740. slot update_slots: id 8 | task 26734 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  741. slot update_slots: id 8 | task 26734 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  742. slot update_slots: id 8 | task 26734 | kv cache rm [0, end)
  743. slot update_slots: id 8 | task 26734 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  744. slot update_slots: id 8 | task 26734 | prompt done, n_past = 199, n_tokens = 261
  745. slot update_slots: id 28 | task 26735 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  746. slot update_slots: id 28 | task 26735 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  747. slot update_slots: id 28 | task 26735 | kv cache rm [0, end)
  748. slot update_slots: id 28 | task 26735 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  749. slot update_slots: id 28 | task 26735 | prompt done, n_past = 199, n_tokens = 460
  750. slot release: id 36 | task 27382 | stop processing: n_past = 172, truncated = 1
  751. slot print_timing: id 36 | task 27382 |
  752. prompt eval time = 1272.89 ms / 199 tokens ( 6.40 ms per token, 156.34 tokens per second)
  753. eval time = 17369.87 ms / 101 tokens ( 171.98 ms per token, 5.81 tokens per second)
  754. total time = 18642.76 ms / 300 tokens
  755. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  756. slot launch_slot_: id 36 | task 26736 | processing task
  757. slot update_slots: id 36 | task 26736 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  758. slot update_slots: id 36 | task 26736 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  759. slot update_slots: id 36 | task 26736 | kv cache rm [0, end)
  760. slot update_slots: id 36 | task 26736 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  761. slot update_slots: id 36 | task 26736 | prompt done, n_past = 199, n_tokens = 262
  762. srv params_from_: Chat format: Content-only
  763. slot release: id 33 | task 26694 | stop processing: n_past = 131, truncated = 1
  764. slot print_timing: id 33 | task 26694 |
  765. prompt eval time = 166.50 ms / 199 tokens ( 0.84 ms per token, 1195.20 tokens per second)
  766. eval time = 11383.52 ms / 60 tokens ( 189.73 ms per token, 5.27 tokens per second)
  767. total time = 11550.02 ms / 259 tokens
  768. slot release: id 56 | task 27388 | stop processing: n_past = 172, truncated = 1
  769. slot print_timing: id 56 | task 27388 |
  770. prompt eval time = 915.36 ms / 199 tokens ( 4.60 ms per token, 217.40 tokens per second)
  771. eval time = 16781.24 ms / 101 tokens ( 166.15 ms per token, 6.02 tokens per second)
  772. total time = 17696.60 ms / 300 tokens
  773. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  774. slot launch_slot_: id 33 | task 27505 | processing task
  775. slot launch_slot_: id 56 | task 26737 | processing task
  776. slot update_slots: id 33 | task 27505 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  777. slot update_slots: id 33 | task 27505 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  778. slot update_slots: id 33 | task 27505 | kv cache rm [0, end)
  779. slot update_slots: id 33 | task 27505 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  780. slot update_slots: id 33 | task 27505 | prompt done, n_past = 199, n_tokens = 261
  781. slot update_slots: id 56 | task 26737 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  782. slot update_slots: id 56 | task 26737 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  783. slot update_slots: id 56 | task 26737 | kv cache rm [0, end)
  784. slot update_slots: id 56 | task 26737 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  785. slot update_slots: id 56 | task 26737 | prompt done, n_past = 199, n_tokens = 460
  786. srv params_from_: Chat format: Content-only
  787. srv cancel_tasks: cancel task, id_task = 27385
  788. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  789. slot release: id 51 | task 27385 | stop processing: n_past = 173, truncated = 1
  790. slot launch_slot_: id 51 | task 27507 | processing task
  791. slot update_slots: id 51 | task 27507 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  792. slot update_slots: id 51 | task 27507 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  793. slot update_slots: id 51 | task 27507 | kv cache rm [0, end)
  794. slot update_slots: id 51 | task 27507 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  795. slot update_slots: id 51 | task 27507 | prompt done, n_past = 199, n_tokens = 262
  796. srv params_from_: Chat format: Content-only
  797. slot update_slots: id 9 | task 26696 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  798. slot update_slots: id 41 | task 26697 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  799. slot update_slots: id 12 | task 26698 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  800. slot update_slots: id 0 | task 26700 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  801. slot update_slots: id 1 | task 26701 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  802. slot update_slots: id 13 | task 26703 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  803. slot update_slots: id 18 | task 26705 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  804. slot release: id 9 | task 26696 | stop processing: n_past = 131, truncated = 1
  805. slot print_timing: id 9 | task 26696 |
  806. prompt eval time = 558.39 ms / 199 tokens ( 2.81 ms per token, 356.38 tokens per second)
  807. eval time = 11177.75 ms / 60 tokens ( 186.30 ms per token, 5.37 tokens per second)
  808. total time = 11736.14 ms / 259 tokens
  809. slot release: id 41 | task 26697 | stop processing: n_past = 131, truncated = 1
  810. slot print_timing: id 41 | task 26697 |
  811. prompt eval time = 566.21 ms / 199 tokens ( 2.85 ms per token, 351.46 tokens per second)
  812. eval time = 11175.86 ms / 60 tokens ( 186.26 ms per token, 5.37 tokens per second)
  813. total time = 11742.07 ms / 259 tokens
  814. srv cancel_tasks: cancel task, id_task = 27390
  815. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  816. slot release: id 52 | task 27390 | stop processing: n_past = 185, truncated = 1
  817. slot launch_slot_: id 9 | task 26740 | processing task
  818. slot launch_slot_: id 41 | task 26741 | processing task
  819. slot launch_slot_: id 52 | task 26742 | processing task
  820. slot update_slots: id 15 | task 26706 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  821. slot update_slots: id 17 | task 26570 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  822. slot update_slots: id 29 | task 26707 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  823. slot update_slots: id 34 | task 26708 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  824. slot update_slots: id 50 | task 27450 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  825. slot update_slots: id 9 | task 26740 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  826. slot update_slots: id 9 | task 26740 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  827. slot update_slots: id 9 | task 26740 | kv cache rm [0, end)
  828. slot update_slots: id 9 | task 26740 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  829. slot update_slots: id 9 | task 26740 | prompt done, n_past = 199, n_tokens = 260
  830. slot update_slots: id 41 | task 26741 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  831. slot update_slots: id 41 | task 26741 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  832. slot update_slots: id 41 | task 26741 | kv cache rm [0, end)
  833. slot update_slots: id 41 | task 26741 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  834. slot update_slots: id 41 | task 26741 | prompt done, n_past = 199, n_tokens = 459
  835. slot update_slots: id 52 | task 26742 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  836. slot update_slots: id 52 | task 26742 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  837. slot update_slots: id 52 | task 26742 | kv cache rm [0, end)
  838. slot update_slots: id 52 | task 26742 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  839. slot update_slots: id 52 | task 26742 | prompt done, n_past = 199, n_tokens = 658
  840. srv params_from_: Chat format: Content-only
  841. slot release: id 12 | task 26698 | stop processing: n_past = 131, truncated = 1
  842. slot print_timing: id 12 | task 26698 |
  843. prompt eval time = 501.51 ms / 199 tokens ( 2.52 ms per token, 396.80 tokens per second)
  844. eval time = 11213.89 ms / 60 tokens ( 186.90 ms per token, 5.35 tokens per second)
  845. total time = 11715.40 ms / 259 tokens
  846. slot launch_slot_: id 12 | task 27525 | processing task
  847. slot update_slots: id 31 | task 26709 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  848. slot update_slots: id 40 | task 26710 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  849. slot update_slots: id 45 | task 27457 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  850. slot update_slots: id 57 | task 26711 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  851. slot update_slots: id 60 | task 27456 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  852. slot update_slots: id 12 | task 27525 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  853. slot update_slots: id 12 | task 27525 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  854. slot update_slots: id 12 | task 27525 | kv cache rm [0, end)
  855. slot update_slots: id 12 | task 27525 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  856. slot update_slots: id 12 | task 27525 | prompt done, n_past = 199, n_tokens = 262
  857. slot release: id 13 | task 26703 | stop processing: n_past = 131, truncated = 1
  858. slot print_timing: id 13 | task 26703 |
  859. prompt eval time = 727.69 ms / 199 tokens ( 3.66 ms per token, 273.47 tokens per second)
  860. eval time = 10817.63 ms / 60 tokens ( 180.29 ms per token, 5.55 tokens per second)
  861. total time = 11545.32 ms / 259 tokens
  862. slot release: id 18 | task 26705 | stop processing: n_past = 131, truncated = 1
  863. slot print_timing: id 18 | task 26705 |
  864. prompt eval time = 729.38 ms / 199 tokens ( 3.67 ms per token, 272.83 tokens per second)
  865. eval time = 10816.39 ms / 60 tokens ( 180.27 ms per token, 5.55 tokens per second)
  866. total time = 11545.76 ms / 259 tokens
  867. slot release: id 29 | task 26707 | stop processing: n_past = 130, truncated = 1
  868. slot print_timing: id 29 | task 26707 |
  869. prompt eval time = 775.95 ms / 199 tokens ( 3.90 ms per token, 256.46 tokens per second)
  870. eval time = 10027.16 ms / 59 tokens ( 169.95 ms per token, 5.88 tokens per second)
  871. total time = 10803.11 ms / 258 tokens
  872. srv cancel_tasks: cancel task, id_task = 27450
  873. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  874. slot release: id 50 | task 27450 | stop processing: n_past = 130, truncated = 1
  875. slot launch_slot_: id 13 | task 26744 | processing task
  876. slot launch_slot_: id 18 | task 26745 | processing task
  877. slot launch_slot_: id 29 | task 26746 | processing task
  878. slot launch_slot_: id 50 | task 26747 | processing task
  879. slot update_slots: id 5 | task 27459 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  880. slot update_slots: id 49 | task 26713 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  881. slot update_slots: id 61 | task 26715 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  882. slot update_slots: id 63 | task 26714 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  883. slot update_slots: id 13 | task 26744 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  884. slot update_slots: id 13 | task 26744 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  885. slot update_slots: id 13 | task 26744 | kv cache rm [0, end)
  886. slot update_slots: id 13 | task 26744 | prompt processing progress, n_past = 199, n_tokens = 259, progress = 1.000000
  887. slot update_slots: id 13 | task 26744 | prompt done, n_past = 199, n_tokens = 259
  888. slot update_slots: id 18 | task 26745 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  889. slot update_slots: id 18 | task 26745 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  890. slot update_slots: id 18 | task 26745 | kv cache rm [0, end)
  891. slot update_slots: id 18 | task 26745 | prompt processing progress, n_past = 199, n_tokens = 458, progress = 1.000000
  892. slot update_slots: id 18 | task 26745 | prompt done, n_past = 199, n_tokens = 458
  893. slot update_slots: id 29 | task 26746 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  894. slot update_slots: id 29 | task 26746 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  895. slot update_slots: id 29 | task 26746 | kv cache rm [0, end)
  896. slot update_slots: id 29 | task 26746 | prompt processing progress, n_past = 199, n_tokens = 657, progress = 1.000000
  897. slot update_slots: id 29 | task 26746 | prompt done, n_past = 199, n_tokens = 657
  898. slot update_slots: id 50 | task 26747 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  899. slot update_slots: id 50 | task 26747 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  900. slot update_slots: id 50 | task 26747 | kv cache rm [0, end)
  901. slot update_slots: id 50 | task 26747 | prompt processing progress, n_past = 199, n_tokens = 856, progress = 1.000000
  902. slot update_slots: id 50 | task 26747 | prompt done, n_past = 199, n_tokens = 856
  903. srv params_from_: Chat format: Content-only
  904. slot release: id 15 | task 26706 | stop processing: n_past = 131, truncated = 1
  905. slot print_timing: id 15 | task 26706 |
  906. prompt eval time = 773.16 ms / 199 tokens ( 3.89 ms per token, 257.39 tokens per second)
  907. eval time = 10671.38 ms / 60 tokens ( 177.86 ms per token, 5.62 tokens per second)
  908. total time = 11444.53 ms / 259 tokens
  909. slot release: id 17 | task 26570 | stop processing: n_past = 131, truncated = 1
  910. slot print_timing: id 17 | task 26570 |
  911. prompt eval time = 773.23 ms / 199 tokens ( 3.89 ms per token, 257.36 tokens per second)
  912. eval time = 10671.41 ms / 60 tokens ( 177.86 ms per token, 5.62 tokens per second)
  913. total time = 11444.63 ms / 259 tokens
  914. slot launch_slot_: id 15 | task 27529 | processing task
  915. slot launch_slot_: id 17 | task 26748 | processing task
  916. slot update_slots: id 21 | task 27462 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  917. slot update_slots: id 15 | task 27529 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  918. slot update_slots: id 15 | task 27529 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  919. slot update_slots: id 15 | task 27529 | kv cache rm [0, end)
  920. slot update_slots: id 15 | task 27529 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  921. slot update_slots: id 15 | task 27529 | prompt done, n_past = 199, n_tokens = 261
  922. slot update_slots: id 17 | task 26748 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  923. slot update_slots: id 17 | task 26748 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  924. slot update_slots: id 17 | task 26748 | kv cache rm [0, end)
  925. slot update_slots: id 17 | task 26748 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  926. slot update_slots: id 17 | task 26748 | prompt done, n_past = 199, n_tokens = 460
  927. slot release: id 40 | task 26710 | stop processing: n_past = 131, truncated = 1
  928. slot print_timing: id 40 | task 26710 |
  929. prompt eval time = 795.32 ms / 199 tokens ( 4.00 ms per token, 250.21 tokens per second)
  930. eval time = 10308.62 ms / 60 tokens ( 171.81 ms per token, 5.82 tokens per second)
  931. total time = 11103.94 ms / 259 tokens
  932. slot release: id 45 | task 27457 | stop processing: n_past = 131, truncated = 1
  933. slot print_timing: id 45 | task 27457 |
  934. prompt eval time = 795.71 ms / 199 tokens ( 4.00 ms per token, 250.09 tokens per second)
  935. eval time = 10309.56 ms / 60 tokens ( 171.83 ms per token, 5.82 tokens per second)
  936. total time = 11105.27 ms / 259 tokens
  937. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  938. slot release: id 57 | task 26711 | stop processing: n_past = 131, truncated = 1
  939. slot print_timing: id 57 | task 26711 |
  940. prompt eval time = 799.07 ms / 199 tokens ( 4.02 ms per token, 249.04 tokens per second)
  941. eval time = 10307.66 ms / 60 tokens ( 171.79 ms per token, 5.82 tokens per second)
  942. total time = 11106.73 ms / 259 tokens
  943. slot launch_slot_: id 40 | task 26750 | processing task
  944. slot launch_slot_: id 45 | task 26751 | processing task
  945. slot launch_slot_: id 57 | task 26752 | processing task
  946. slot update_slots: id 58 | task 26719 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  947. slot update_slots: id 40 | task 26750 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  948. slot update_slots: id 40 | task 26750 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  949. slot update_slots: id 40 | task 26750 | kv cache rm [0, end)
  950. slot update_slots: id 40 | task 26750 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  951. slot update_slots: id 40 | task 26750 | prompt done, n_past = 199, n_tokens = 260
  952. slot update_slots: id 45 | task 26751 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  953. slot update_slots: id 45 | task 26751 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  954. slot update_slots: id 45 | task 26751 | kv cache rm [0, end)
  955. slot update_slots: id 45 | task 26751 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  956. slot update_slots: id 45 | task 26751 | prompt done, n_past = 199, n_tokens = 459
  957. slot update_slots: id 57 | task 26752 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  958. slot update_slots: id 57 | task 26752 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  959. slot update_slots: id 57 | task 26752 | kv cache rm [0, end)
  960. slot update_slots: id 57 | task 26752 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  961. slot update_slots: id 57 | task 26752 | prompt done, n_past = 199, n_tokens = 658
  962. srv params_from_: Chat format: Content-only
  963. slot release: id 2 | task 26638 | stop processing: n_past = 194, truncated = 1
  964. slot print_timing: id 2 | task 26638 |
  965. prompt eval time = 1083.46 ms / 199 tokens ( 5.44 ms per token, 183.67 tokens per second)
  966. eval time = 24183.77 ms / 123 tokens ( 196.62 ms per token, 5.09 tokens per second)
  967. total time = 25267.23 ms / 322 tokens
  968. slot release: id 5 | task 27459 | stop processing: n_past = 131, truncated = 1
  969. slot print_timing: id 5 | task 27459 |
  970. prompt eval time = 631.25 ms / 199 tokens ( 3.17 ms per token, 315.25 tokens per second)
  971. eval time = 10203.12 ms / 60 tokens ( 170.05 ms per token, 5.88 tokens per second)
  972. total time = 10834.36 ms / 259 tokens
  973. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  974. srv params_from_: Chat format: Content-only
  975. slot release: id 63 | task 26714 | stop processing: n_past = 131, truncated = 1
  976. slot print_timing: id 63 | task 26714 |
  977. prompt eval time = 641.80 ms / 199 tokens ( 3.23 ms per token, 310.07 tokens per second)
  978. eval time = 10204.05 ms / 60 tokens ( 170.07 ms per token, 5.88 tokens per second)
  979. total time = 10845.85 ms / 259 tokens
  980. slot launch_slot_: id 2 | task 27532 | processing task
  981. slot launch_slot_: id 5 | task 26753 | processing task
  982. slot launch_slot_: id 63 | task 26754 | processing task
  983. slot update_slots: id 2 | task 27532 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  984. slot update_slots: id 2 | task 27532 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  985. slot update_slots: id 2 | task 27532 | kv cache rm [0, end)
  986. slot update_slots: id 2 | task 27532 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  987. slot update_slots: id 2 | task 27532 | prompt done, n_past = 199, n_tokens = 260
  988. slot update_slots: id 5 | task 26753 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  989. slot update_slots: id 5 | task 26753 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  990. slot update_slots: id 5 | task 26753 | kv cache rm [0, end)
  991. slot update_slots: id 5 | task 26753 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  992. slot update_slots: id 5 | task 26753 | prompt done, n_past = 199, n_tokens = 459
  993. slot update_slots: id 63 | task 26754 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  994. slot update_slots: id 63 | task 26754 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  995. slot update_slots: id 63 | task 26754 | kv cache rm [0, end)
  996. slot update_slots: id 63 | task 26754 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  997. slot update_slots: id 63 | task 26754 | prompt done, n_past = 199, n_tokens = 658
  998. slot release: id 21 | task 27462 | stop processing: n_past = 131, truncated = 1
  999. slot print_timing: id 21 | task 27462 |
  1000. prompt eval time = 447.23 ms / 199 tokens ( 2.25 ms per token, 444.96 tokens per second)
  1001. eval time = 10285.98 ms / 60 tokens ( 171.43 ms per token, 5.83 tokens per second)
  1002. total time = 10733.21 ms / 259 tokens
  1003. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1004. slot release: id 58 | task 26719 | stop processing: n_past = 130, truncated = 1
  1005. slot print_timing: id 58 | task 26719 |
  1006. prompt eval time = 362.73 ms / 199 tokens ( 1.82 ms per token, 548.61 tokens per second)
  1007. eval time = 9919.69 ms / 59 tokens ( 168.13 ms per token, 5.95 tokens per second)
  1008. total time = 10282.42 ms / 258 tokens
  1009. srv params_from_: Chat format: Content-only
  1010. slot launch_slot_: id 21 | task 26756 | processing task
  1011. slot launch_slot_: id 58 | task 26757 | processing task
  1012. slot update_slots: id 27 | task 27467 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1013. slot update_slots: id 21 | task 26756 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1014. slot update_slots: id 21 | task 26756 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1015. slot update_slots: id 21 | task 26756 | kv cache rm [0, end)
  1016. slot update_slots: id 21 | task 26756 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1017. slot update_slots: id 21 | task 26756 | prompt done, n_past = 199, n_tokens = 261
  1018. slot update_slots: id 58 | task 26757 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1019. slot update_slots: id 58 | task 26757 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1020. slot update_slots: id 58 | task 26757 | kv cache rm [0, end)
  1021. slot update_slots: id 58 | task 26757 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1022. slot update_slots: id 58 | task 26757 | prompt done, n_past = 199, n_tokens = 460
  1023. srv cancel_tasks: cancel task, id_task = 27456
  1024. slot update_slots: id 16 | task 26582 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1025. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1026. srv params_from_: Chat format: Content-only
  1027. srv cancel_tasks: cancel task, id_task = 27467
  1028. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1029. srv cancel_tasks: cancel task, id_task = 27505
  1030. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1031. srv params_from_: Chat format: Content-only
  1032. slot release: id 33 | task 27505 | stop processing: n_past = 220, truncated = 1
  1033. slot release: id 27 | task 27467 | stop processing: n_past = 130, truncated = 1
  1034. slot release: id 60 | task 27456 | stop processing: n_past = 135, truncated = 1
  1035. slot launch_slot_: id 33 | task 27539 | processing task
  1036. slot launch_slot_: id 27 | task 27542 | processing task
  1037. srv params_from_: Chat format: Content-only
  1038. slot launch_slot_: id 60 | task 26758 | processing task
  1039. slot update_slots: id 38 | task 26598 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1040. slot update_slots: id 44 | task 26608 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1041. slot update_slots: id 27 | task 27542 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1042. slot update_slots: id 27 | task 27542 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1043. slot update_slots: id 27 | task 27542 | kv cache rm [0, end)
  1044. slot update_slots: id 27 | task 27542 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  1045. slot update_slots: id 27 | task 27542 | prompt done, n_past = 199, n_tokens = 260
  1046. slot update_slots: id 33 | task 27539 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1047. slot update_slots: id 33 | task 27539 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1048. slot update_slots: id 33 | task 27539 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1049. slot update_slots: id 33 | task 27539 | kv cache rm [198, end)
  1050. slot update_slots: id 33 | task 27539 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 0.005025
  1051. slot update_slots: id 33 | task 27539 | prompt done, n_past = 199, n_tokens = 261
  1052. slot update_slots: id 60 | task 26758 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1053. slot update_slots: id 60 | task 26758 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1054. slot update_slots: id 60 | task 26758 | kv cache rm [0, end)
  1055. slot update_slots: id 60 | task 26758 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1056. slot update_slots: id 60 | task 26758 | prompt done, n_past = 199, n_tokens = 460
  1057. slot update_slots: id 62 | task 26614 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1058. srv cancel_tasks: cancel task, id_task = 27507
  1059. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1060. slot release: id 51 | task 27507 | stop processing: n_past = 221, truncated = 1
  1061. slot launch_slot_: id 51 | task 26761 | processing task
  1062. slot update_slots: id 51 | task 26761 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1063. slot update_slots: id 51 | task 26761 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1064. slot update_slots: id 51 | task 26761 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1065. slot update_slots: id 51 | task 26761 | kv cache rm [198, end)
  1066. slot update_slots: id 51 | task 26761 | prompt processing progress, n_past = 199, n_tokens = 64, progress = 0.005025
  1067. slot update_slots: id 51 | task 26761 | prompt done, n_past = 199, n_tokens = 64
  1068. srv params_from_: Chat format: Content-only
  1069. slot update_slots: id 3 | task 26721 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1070. slot update_slots: id 10 | task 26722 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1071. slot update_slots: id 20 | task 26723 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1072. slot update_slots: id 32 | task 26724 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1073. slot update_slots: id 47 | task 26725 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1074. slot release: id 3 | task 26721 | stop processing: n_past = 131, truncated = 1
  1075. slot print_timing: id 3 | task 26721 |
  1076. prompt eval time = 501.75 ms / 199 tokens ( 2.52 ms per token, 396.62 tokens per second)
  1077. eval time = 10465.31 ms / 60 tokens ( 174.42 ms per token, 5.73 tokens per second)
  1078. total time = 10967.05 ms / 259 tokens
  1079. slot release: id 20 | task 26723 | stop processing: n_past = 131, truncated = 1
  1080. slot print_timing: id 20 | task 26723 |
  1081. prompt eval time = 504.14 ms / 199 tokens ( 2.53 ms per token, 394.73 tokens per second)
  1082. eval time = 10466.52 ms / 60 tokens ( 174.44 ms per token, 5.73 tokens per second)
  1083. total time = 10970.66 ms / 259 tokens
  1084. slot release: id 26 | task 26641 | stop processing: n_past = 203, truncated = 1
  1085. slot print_timing: id 26 | task 26641 |
  1086. prompt eval time = 1085.37 ms / 199 tokens ( 5.45 ms per token, 183.35 tokens per second)
  1087. eval time = 26787.91 ms / 132 tokens ( 202.94 ms per token, 4.93 tokens per second)
  1088. total time = 27873.28 ms / 331 tokens
  1089. slot release: id 32 | task 26724 | stop processing: n_past = 131, truncated = 1
  1090. slot print_timing: id 32 | task 26724 |
  1091. prompt eval time = 506.59 ms / 199 tokens ( 2.55 ms per token, 392.82 tokens per second)
  1092. eval time = 10466.03 ms / 60 tokens ( 174.43 ms per token, 5.73 tokens per second)
  1093. total time = 10972.62 ms / 259 tokens
  1094. slot release: id 47 | task 26725 | stop processing: n_past = 131, truncated = 1
  1095. slot print_timing: id 47 | task 26725 |
  1096. prompt eval time = 509.36 ms / 199 tokens ( 2.56 ms per token, 390.69 tokens per second)
  1097. eval time = 10465.44 ms / 60 tokens ( 174.42 ms per token, 5.73 tokens per second)
  1098. total time = 10974.80 ms / 259 tokens
  1099. slot launch_slot_: id 3 | task 26762 | processing task
  1100. slot launch_slot_: id 20 | task 26763 | processing task
  1101. slot launch_slot_: id 26 | task 26764 | processing task
  1102. slot launch_slot_: id 32 | task 26767 | processing task
  1103. slot launch_slot_: id 47 | task 26768 | processing task
  1104. slot update_slots: id 3 | task 26762 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1105. slot update_slots: id 3 | task 26762 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1106. slot update_slots: id 3 | task 26762 | kv cache rm [0, end)
  1107. slot update_slots: id 3 | task 26762 | prompt processing progress, n_past = 199, n_tokens = 258, progress = 1.000000
  1108. slot update_slots: id 3 | task 26762 | prompt done, n_past = 199, n_tokens = 258
  1109. slot update_slots: id 20 | task 26763 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1110. slot update_slots: id 20 | task 26763 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1111. slot update_slots: id 20 | task 26763 | kv cache rm [0, end)
  1112. slot update_slots: id 20 | task 26763 | prompt processing progress, n_past = 199, n_tokens = 457, progress = 1.000000
  1113. slot update_slots: id 20 | task 26763 | prompt done, n_past = 199, n_tokens = 457
  1114. slot update_slots: id 26 | task 26764 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1115. slot update_slots: id 26 | task 26764 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1116. slot update_slots: id 26 | task 26764 | kv cache rm [0, end)
  1117. slot update_slots: id 26 | task 26764 | prompt processing progress, n_past = 199, n_tokens = 656, progress = 1.000000
  1118. slot update_slots: id 26 | task 26764 | prompt done, n_past = 199, n_tokens = 656
  1119. slot update_slots: id 32 | task 26767 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1120. slot update_slots: id 32 | task 26767 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1121. slot update_slots: id 32 | task 26767 | kv cache rm [0, end)
  1122. slot update_slots: id 32 | task 26767 | prompt processing progress, n_past = 199, n_tokens = 855, progress = 1.000000
  1123. slot update_slots: id 32 | task 26767 | prompt done, n_past = 199, n_tokens = 855
  1124. slot update_slots: id 47 | task 26768 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1125. slot update_slots: id 47 | task 26768 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1126. slot update_slots: id 47 | task 26768 | kv cache rm [0, end)
  1127. slot update_slots: id 47 | task 26768 | prompt processing progress, n_past = 199, n_tokens = 1054, progress = 1.000000
  1128. slot update_slots: id 47 | task 26768 | prompt done, n_past = 199, n_tokens = 1054
  1129. srv cancel_tasks: cancel task, id_task = 27525
  1130. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1131. slot release: id 46 | task 26654 | stop processing: n_past = 203, truncated = 1
  1132. slot print_timing: id 46 | task 26654 |
  1133. prompt eval time = 1275.27 ms / 199 tokens ( 6.41 ms per token, 156.05 tokens per second)
  1134. eval time = 25284.77 ms / 132 tokens ( 191.55 ms per token, 5.22 tokens per second)
  1135. total time = 26560.04 ms / 331 tokens
  1136. srv params_from_: Chat format: Content-only
  1137. slot release: id 12 | task 27525 | stop processing: n_past = 213, truncated = 1
  1138. slot launch_slot_: id 46 | task 26775 | processing task
  1139. slot launch_slot_: id 12 | task 27555 | processing task
  1140. slot update_slots: id 12 | task 27555 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1141. slot update_slots: id 12 | task 27555 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1142. slot update_slots: id 12 | task 27555 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1143. slot update_slots: id 12 | task 27555 | kv cache rm [198, end)
  1144. slot update_slots: id 12 | task 27555 | prompt processing progress, n_past = 199, n_tokens = 63, progress = 0.005025
  1145. slot update_slots: id 12 | task 27555 | prompt done, n_past = 199, n_tokens = 63
  1146. slot update_slots: id 46 | task 26775 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1147. slot update_slots: id 46 | task 26775 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1148. slot update_slots: id 46 | task 26775 | kv cache rm [0, end)
  1149. slot update_slots: id 46 | task 26775 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1150. slot update_slots: id 46 | task 26775 | prompt done, n_past = 199, n_tokens = 262
  1151. slot release: id 53 | task 26683 | stop processing: n_past = 194, truncated = 1
  1152. slot print_timing: id 53 | task 26683 |
  1153. prompt eval time = 440.08 ms / 199 tokens ( 2.21 ms per token, 452.19 tokens per second)
  1154. eval time = 23202.50 ms / 123 tokens ( 188.64 ms per token, 5.30 tokens per second)
  1155. total time = 23642.58 ms / 322 tokens
  1156. slot launch_slot_: id 53 | task 26776 | processing task
  1157. slot update_slots: id 53 | task 26776 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1158. slot update_slots: id 53 | task 26776 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1159. slot update_slots: id 53 | task 26776 | kv cache rm [0, end)
  1160. slot update_slots: id 53 | task 26776 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1161. slot update_slots: id 53 | task 26776 | prompt done, n_past = 199, n_tokens = 262
  1162. srv cancel_tasks: cancel task, id_task = 27532
  1163. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1164. srv cancel_tasks: cancel task, id_task = 27529
  1165. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1166. srv params_from_: Chat format: Content-only
  1167. srv params_from_: Chat format: Content-only
  1168. slot release: id 15 | task 27529 | stop processing: n_past = 213, truncated = 1
  1169. slot release: id 2 | task 27532 | stop processing: n_past = 211, truncated = 1
  1170. slot launch_slot_: id 15 | task 27560 | processing task
  1171. slot launch_slot_: id 2 | task 27561 | processing task
  1172. slot update_slots: id 2 | task 27561 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1173. slot update_slots: id 2 | task 27561 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1174. slot update_slots: id 2 | task 27561 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1175. slot update_slots: id 2 | task 27561 | kv cache rm [198, end)
  1176. slot update_slots: id 2 | task 27561 | prompt processing progress, n_past = 199, n_tokens = 63, progress = 0.005025
  1177. slot update_slots: id 2 | task 27561 | prompt done, n_past = 199, n_tokens = 63
  1178. slot update_slots: id 15 | task 27560 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1179. slot update_slots: id 15 | task 27560 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1180. slot update_slots: id 15 | task 27560 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1181. slot update_slots: id 15 | task 27560 | kv cache rm [198, end)
  1182. slot update_slots: id 15 | task 27560 | prompt processing progress, n_past = 199, n_tokens = 64, progress = 0.005025
  1183. slot update_slots: id 15 | task 27560 | prompt done, n_past = 199, n_tokens = 64
  1184. slot update_slots: id 59 | task 26726 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1185. slot release: id 59 | task 26726 | stop processing: n_past = 131, truncated = 1
  1186. slot print_timing: id 59 | task 26726 |
  1187. prompt eval time = 160.42 ms / 199 tokens ( 0.81 ms per token, 1240.49 tokens per second)
  1188. eval time = 11730.88 ms / 60 tokens ( 195.51 ms per token, 5.11 tokens per second)
  1189. total time = 11891.30 ms / 259 tokens
  1190. slot launch_slot_: id 59 | task 26787 | processing task
  1191. slot update_slots: id 59 | task 26787 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1192. slot update_slots: id 59 | task 26787 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1193. slot update_slots: id 59 | task 26787 | kv cache rm [0, end)
  1194. slot update_slots: id 59 | task 26787 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1195. slot update_slots: id 59 | task 26787 | prompt done, n_past = 199, n_tokens = 262
  1196. slot update_slots: id 42 | task 26727 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1197. srv cancel_tasks: cancel task, id_task = 27539
  1198. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1199. slot release: id 42 | task 26727 | stop processing: n_past = 131, truncated = 1
  1200. slot print_timing: id 42 | task 26727 |
  1201. prompt eval time = 156.80 ms / 199 tokens ( 0.79 ms per token, 1269.17 tokens per second)
  1202. eval time = 11525.93 ms / 60 tokens ( 192.10 ms per token, 5.21 tokens per second)
  1203. total time = 11682.73 ms / 259 tokens
  1204. slot release: id 33 | task 27539 | stop processing: n_past = 217, truncated = 1
  1205. slot launch_slot_: id 42 | task 26789 | processing task
  1206. slot launch_slot_: id 33 | task 26790 | processing task
  1207. slot update_slots: id 33 | task 26790 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1208. slot update_slots: id 33 | task 26790 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1209. slot update_slots: id 33 | task 26790 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1210. slot update_slots: id 33 | task 26790 | kv cache rm [198, end)
  1211. slot update_slots: id 33 | task 26790 | prompt processing progress, n_past = 199, n_tokens = 63, progress = 0.005025
  1212. slot update_slots: id 33 | task 26790 | prompt done, n_past = 199, n_tokens = 63
  1213. slot update_slots: id 42 | task 26789 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1214. slot update_slots: id 42 | task 26789 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1215. slot update_slots: id 42 | task 26789 | kv cache rm [0, end)
  1216. slot update_slots: id 42 | task 26789 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1217. slot update_slots: id 42 | task 26789 | prompt done, n_past = 199, n_tokens = 262
  1218. srv params_from_: Chat format: Content-only
  1219. srv cancel_tasks: cancel task, id_task = 27542
  1220. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1221. slot release: id 27 | task 27542 | stop processing: n_past = 223, truncated = 1
  1222. slot launch_slot_: id 27 | task 26791 | processing task
  1223. slot update_slots: id 27 | task 26791 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1224. slot update_slots: id 27 | task 26791 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1225. slot update_slots: id 27 | task 26791 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1226. slot update_slots: id 27 | task 26791 | kv cache rm [198, end)
  1227. slot update_slots: id 27 | task 26791 | prompt processing progress, n_past = 199, n_tokens = 64, progress = 0.005025
  1228. slot update_slots: id 27 | task 26791 | prompt done, n_past = 199, n_tokens = 64
  1229. srv params_from_: Chat format: Content-only
  1230. slot update_slots: id 4 | task 26573 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1231. slot release: id 4 | task 26573 | stop processing: n_past = 131, truncated = 1
  1232. slot print_timing: id 4 | task 26573 |
  1233. prompt eval time = 160.19 ms / 199 tokens ( 0.80 ms per token, 1242.24 tokens per second)
  1234. eval time = 11820.64 ms / 60 tokens ( 197.01 ms per token, 5.08 tokens per second)
  1235. total time = 11980.84 ms / 259 tokens
  1236. srv cancel_tasks: cancel task, id_task = 27560
  1237. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1238. srv cancel_tasks: cancel task, id_task = 27555
  1239. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1240. slot release: id 12 | task 27555 | stop processing: n_past = 221, truncated = 1
  1241. slot release: id 15 | task 27560 | stop processing: n_past = 219, truncated = 1
  1242. slot launch_slot_: id 4 | task 26792 | processing task
  1243. slot launch_slot_: id 12 | task 26793 | processing task
  1244. slot launch_slot_: id 15 | task 26795 | processing task
  1245. slot update_slots: id 7 | task 26728 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1246. slot update_slots: id 39 | task 26729 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1247. slot update_slots: id 4 | task 26792 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1248. slot update_slots: id 4 | task 26792 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1249. slot update_slots: id 4 | task 26792 | kv cache rm [0, end)
  1250. slot update_slots: id 4 | task 26792 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  1251. slot update_slots: id 4 | task 26792 | prompt done, n_past = 199, n_tokens = 260
  1252. slot update_slots: id 12 | task 26793 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1253. slot update_slots: id 12 | task 26793 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1254. slot update_slots: id 12 | task 26793 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1255. slot update_slots: id 12 | task 26793 | kv cache rm [198, end)
  1256. slot update_slots: id 12 | task 26793 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 0.005025
  1257. slot update_slots: id 12 | task 26793 | prompt done, n_past = 199, n_tokens = 261
  1258. slot update_slots: id 15 | task 26795 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1259. slot update_slots: id 15 | task 26795 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1260. slot update_slots: id 15 | task 26795 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1261. slot update_slots: id 15 | task 26795 | kv cache rm [198, end)
  1262. slot update_slots: id 15 | task 26795 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 0.005025
  1263. slot update_slots: id 15 | task 26795 | prompt done, n_past = 199, n_tokens = 262
  1264. srv params_from_: Chat format: Content-only
  1265. srv params_from_: Chat format: Content-only
  1266. slot update_slots: id 11 | task 26732 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1267. slot release: id 7 | task 26728 | stop processing: n_past = 130, truncated = 1
  1268. slot print_timing: id 7 | task 26728 |
  1269. prompt eval time = 238.69 ms / 199 tokens ( 1.20 ms per token, 833.71 tokens per second)
  1270. eval time = 11545.66 ms / 59 tokens ( 195.69 ms per token, 5.11 tokens per second)
  1271. total time = 11784.35 ms / 258 tokens
  1272. slot release: id 39 | task 26729 | stop processing: n_past = 130, truncated = 1
  1273. slot print_timing: id 39 | task 26729 |
  1274. prompt eval time = 243.93 ms / 199 tokens ( 1.23 ms per token, 815.81 tokens per second)
  1275. eval time = 11543.04 ms / 59 tokens ( 195.64 ms per token, 5.11 tokens per second)
  1276. total time = 11786.97 ms / 258 tokens
  1277. slot launch_slot_: id 7 | task 26802 | processing task
  1278. slot launch_slot_: id 39 | task 26805 | processing task
  1279. slot update_slots: id 8 | task 26734 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1280. slot update_slots: id 28 | task 26735 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1281. slot update_slots: id 7 | task 26802 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1282. slot update_slots: id 7 | task 26802 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1283. slot update_slots: id 7 | task 26802 | kv cache rm [0, end)
  1284. slot update_slots: id 7 | task 26802 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1285. slot update_slots: id 7 | task 26802 | prompt done, n_past = 199, n_tokens = 261
  1286. slot update_slots: id 39 | task 26805 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1287. slot update_slots: id 39 | task 26805 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1288. slot update_slots: id 39 | task 26805 | kv cache rm [0, end)
  1289. slot update_slots: id 39 | task 26805 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1290. slot update_slots: id 39 | task 26805 | prompt done, n_past = 199, n_tokens = 460
  1291. srv cancel_tasks: cancel task, id_task = 27561
  1292. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1293. slot release: id 2 | task 27561 | stop processing: n_past = 222, truncated = 1
  1294. srv params_from_: Chat format: Content-only
  1295. slot launch_slot_: id 2 | task 26807 | processing task
  1296. slot update_slots: id 24 | task 26621 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1297. slot update_slots: id 36 | task 26736 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1298. slot update_slots: id 2 | task 26807 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1299. slot update_slots: id 2 | task 26807 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1300. slot update_slots: id 2 | task 26807 | need to evaluate at least 1 token to generate logits, n_past = 199, n_prompt_tokens = 199
  1301. slot update_slots: id 2 | task 26807 | kv cache rm [198, end)
  1302. slot update_slots: id 2 | task 26807 | prompt processing progress, n_past = 199, n_tokens = 64, progress = 0.005025
  1303. slot update_slots: id 2 | task 26807 | prompt done, n_past = 199, n_tokens = 64
  1304. slot release: id 11 | task 26732 | stop processing: n_past = 131, truncated = 1
  1305. slot print_timing: id 11 | task 26732 |
  1306. prompt eval time = 321.99 ms / 199 tokens ( 1.62 ms per token, 618.04 tokens per second)
  1307. eval time = 11707.64 ms / 60 tokens ( 195.13 ms per token, 5.12 tokens per second)
  1308. total time = 12029.62 ms / 259 tokens
  1309. slot launch_slot_: id 11 | task 26813 | processing task
  1310. slot update_slots: id 56 | task 26737 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1311. slot update_slots: id 11 | task 26813 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1312. slot update_slots: id 11 | task 26813 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1313. slot update_slots: id 11 | task 26813 | kv cache rm [0, end)
  1314. slot update_slots: id 11 | task 26813 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1315. slot update_slots: id 11 | task 26813 | prompt done, n_past = 199, n_tokens = 262
  1316. slot release: id 34 | task 26708 | stop processing: n_past = 172, truncated = 1
  1317. slot print_timing: id 34 | task 26708 |
  1318. prompt eval time = 777.04 ms / 199 tokens ( 3.90 ms per token, 256.10 tokens per second)
  1319. eval time = 19166.72 ms / 101 tokens ( 189.77 ms per token, 5.27 tokens per second)
  1320. total time = 19943.76 ms / 300 tokens
  1321. slot launch_slot_: id 34 | task 26816 | processing task
  1322. slot update_slots: id 34 | task 26816 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1323. slot update_slots: id 34 | task 26816 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1324. slot update_slots: id 34 | task 26816 | kv cache rm [0, end)
  1325. slot update_slots: id 34 | task 26816 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1326. slot update_slots: id 34 | task 26816 | prompt done, n_past = 199, n_tokens = 262
  1327. slot release: id 31 | task 26709 | stop processing: n_past = 172, truncated = 1
  1328. slot print_timing: id 31 | task 26709 |
  1329. prompt eval time = 793.57 ms / 199 tokens ( 3.99 ms per token, 250.77 tokens per second)
  1330. eval time = 18526.44 ms / 101 tokens ( 183.43 ms per token, 5.45 tokens per second)
  1331. total time = 19320.01 ms / 300 tokens
  1332. slot release: id 36 | task 26736 | stop processing: n_past = 131, truncated = 1
  1333. slot print_timing: id 36 | task 26736 |
  1334. prompt eval time = 323.19 ms / 199 tokens ( 1.62 ms per token, 615.74 tokens per second)
  1335. eval time = 11726.21 ms / 60 tokens ( 195.44 ms per token, 5.12 tokens per second)
  1336. total time = 12049.40 ms / 259 tokens
  1337. slot launch_slot_: id 31 | task 26818 | processing task
  1338. slot launch_slot_: id 36 | task 26819 | processing task
  1339. slot update_slots: id 31 | task 26818 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1340. slot update_slots: id 31 | task 26818 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1341. slot update_slots: id 31 | task 26818 | kv cache rm [0, end)
  1342. slot update_slots: id 31 | task 26818 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1343. slot update_slots: id 31 | task 26818 | prompt done, n_past = 199, n_tokens = 261
  1344. slot update_slots: id 36 | task 26819 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1345. slot update_slots: id 36 | task 26819 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1346. slot update_slots: id 36 | task 26819 | kv cache rm [0, end)
  1347. slot update_slots: id 36 | task 26819 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1348. slot update_slots: id 36 | task 26819 | prompt done, n_past = 199, n_tokens = 460
  1349. srv cancel_tasks: cancel task, id_task = 27248
  1350. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1351. srv cancel_tasks: cancel task, id_task = 27358
  1352. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1353. srv cancel_tasks: cancel task, id_task = 27348
  1354. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1355. srv cancel_tasks: cancel task, id_task = 27262
  1356. srv cancel_tasks: cancel task, id_task = 27548
  1357. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1358. srv cancel_tasks: cancel task, id_task = 27356
  1359. srv cancel_tasks: cancel task, id_task = 27266
  1360. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1361. srv cancel_tasks: cancel task, id_task = 27213
  1362. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1363. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1364. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1365. srv cancel_tasks: cancel task, id_task = 27201
  1366. srv cancel_tasks: cancel task, id_task = 27264
  1367. srv cancel_tasks: cancel task, id_task = 27215
  1368. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1369. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1370. srv cancel_tasks: cancel task, id_task = 27345
  1371. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1372. srv cancel_tasks: cancel task, id_task = 27250
  1373. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1374. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1375. srv cancel_tasks: cancel task, id_task = 27265
  1376. srv cancel_tasks: cancel task, id_task = 27451
  1377. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1378. srv cancel_tasks: cancel task, id_task = 27224
  1379. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1380. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1381. srv cancel_tasks: cancel task, id_task = 27377
  1382. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1383. srv cancel_tasks: cancel task, id_task = 27452
  1384. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1385. srv params_from_: Chat format: Content-only
  1386. srv params_from_: Chat format: Content-only
  1387. srv params_from_: Chat format: Content-only
  1388. srv cancel_tasks: cancel task, id_task = 27232
  1389. srv cancel_tasks: cancel task, id_task = 27355
  1390. srv params_from_: Chat format: Content-only
  1391. srv cancel_tasks: cancel task, id_task = 27206
  1392. srv params_from_: Chat format: Content-only
  1393. srv cancel_tasks: cancel task, id_task = 27251
  1394. srv params_from_: Chat format: Content-only
  1395. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1396. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1397. srv cancel_tasks: cancel task, id_task = 27365
  1398. srv params_from_: Chat format: Content-only
  1399. srv cancel_tasks: cancel task, id_task = 27249
  1400. srv params_from_: Chat format: Content-only
  1401. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1402. srv params_from_: Chat format: Content-only
  1403. srv cancel_tasks: cancel task, id_task = 27234
  1404. srv cancel_tasks: cancel task, id_task = 27573
  1405. srv params_from_: Chat format: Content-only
  1406. srv cancel_tasks: cancel task, id_task = 27261
  1407. srv params_from_: Chat format: Content-only
  1408. srv cancel_tasks: cancel task, id_task = 27230
  1409. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1410. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1411. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1412. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1413. srv cancel_tasks: cancel task, id_task = 27218
  1414. srv cancel_tasks: cancel task, id_task = 27360
  1415. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1416. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1417. srv params_from_: Chat format: Content-only
  1418. srv cancel_tasks: cancel task, id_task = 27543
  1419. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1420. srv params_from_: Chat format: Content-only
  1421. srv params_from_: Chat format: Content-only
  1422. srv cancel_tasks: cancel task, id_task = 27376
  1423. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1424. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1425. srv params_from_: Chat format: Content-only
  1426. srv cancel_tasks: cancel task, id_task = 27208
  1427. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1428. srv cancel_tasks: cancel task, id_task = 27357
  1429. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1430. srv cancel_tasks: cancel task, id_task = 27453
  1431. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1432. srv cancel_tasks: cancel task, id_task = 27367
  1433. srv cancel_tasks: cancel task, id_task = 27214
  1434. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1435. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1436. srv params_from_: Chat format: Content-only
  1437. srv params_from_: Chat format: Content-only
  1438. srv cancel_tasks: cancel task, id_task = 27535
  1439. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1440. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1441. srv params_from_: Chat format: Content-only
  1442. srv params_from_: Chat format: Content-only
  1443. srv params_from_: Chat format: Content-only
  1444. srv cancel_tasks: cancel task, id_task = 27223
  1445. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1446. srv params_from_: Chat format: Content-only
  1447. srv cancel_tasks: cancel task, id_task = 27368
  1448. srv cancel_tasks: cancel task, id_task = 27202
  1449. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1450. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1451. srv cancel_tasks: cancel task, id_task = 27510
  1452. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1453. srv params_from_: Chat format: Content-only
  1454. srv params_from_: Chat format: Content-only
  1455. srv cancel_tasks: cancel task, id_task = 27581
  1456. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1457. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1458. srv params_from_: Chat format: Content-only
  1459. srv cancel_tasks: cancel task, id_task = 27591
  1460. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1461. srv params_from_: Chat format: Content-only
  1462. srv cancel_tasks: cancel task, id_task = 27359
  1463. srv params_from_: Chat format: Content-only
  1464. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1465. srv params_from_: Chat format: Content-only
  1466. srv cancel_tasks: cancel task, id_task = 27216
  1467. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1468. srv cancel_tasks: cancel task, id_task = 27238
  1469. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1470. srv params_from_: Chat format: Content-only
  1471. srv cancel_tasks: cancel task, id_task = 27346
  1472. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1473. srv cancel_tasks: cancel task, id_task = 27533
  1474. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1475. srv params_from_: Chat format: Content-only
  1476. srv cancel_tasks: cancel task, id_task = 27375
  1477. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1478. srv params_from_: Chat format: Content-only
  1479. srv cancel_tasks: cancel task, id_task = 27236
  1480. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1481. srv cancel_tasks: cancel task, id_task = 27447
  1482. srv cancel_tasks: cancel task, id_task = 27343
  1483. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1484. srv cancel_tasks: cancel task, id_task = 27253
  1485. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1486. srv cancel_tasks: cancel task, id_task = 27344
  1487. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1488. srv params_from_: Chat format: Content-only
  1489. srv params_from_: Chat format: Content-only
  1490. srv params_from_: Chat format: Content-only
  1491. srv cancel_tasks: cancel task, id_task = 27240
  1492. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1493. srv params_from_: Chat format: Content-only
  1494. srv params_from_: Chat format: Content-only
  1495. srv params_from_: Chat format: Content-only
  1496. srv cancel_tasks: cancel task, id_task = 27378
  1497. srv cancel_tasks: cancel task, id_task = 27226
  1498. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1499. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1500. srv cancel_tasks: cancel task, id_task = 27263
  1501. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1502. srv params_from_: Chat format: Content-only
  1503. srv cancel_tasks: cancel task, id_task = 27370
  1504. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1505. srv params_from_: Chat format: Content-only
  1506. srv cancel_tasks: cancel task, id_task = 27207
  1507. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1508. srv params_from_: Chat format: Content-only
  1509. srv cancel_tasks: cancel task, id_task = 27366
  1510. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1511. srv cancel_tasks: cancel task, id_task = 27225
  1512. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1513. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1514. srv params_from_: Chat format: Content-only
  1515. srv params_from_: Chat format: Content-only
  1516. srv params_from_: Chat format: Content-only
  1517. srv params_from_: Chat format: Content-only
  1518. srv params_from_: Chat format: Content-only
  1519. srv params_from_: Chat format: Content-only
  1520. srv params_from_: Chat format: Content-only
  1521. srv params_from_: Chat format: Content-only
  1522. srv params_from_: Chat format: Content-only
  1523. srv params_from_: Chat format: Content-only
  1524. srv params_from_: Chat format: Content-only
  1525. srv params_from_: Chat format: Content-only
  1526. srv params_from_: Chat format: Content-only
  1527. srv params_from_: Chat format: Content-only
  1528. srv params_from_: Chat format: Content-only
  1529. srv params_from_: Chat format: Content-only
  1530. srv params_from_: Chat format: Content-only
  1531. srv params_from_: Chat format: Content-only
  1532. srv params_from_: Chat format: Content-only
  1533. srv params_from_: Chat format: Content-only
  1534. srv params_from_: Chat format: Content-only
  1535. srv params_from_: Chat format: Content-only
  1536. srv params_from_: Chat format: Content-only
  1537. srv params_from_: Chat format: Content-only
  1538. srv cancel_tasks: cancel task, id_task = 27247
  1539. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1540. srv params_from_: Chat format: Content-only
  1541. slot update_slots: id 14 | task 26627 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1542. slot release: id 10 | task 26722 | stop processing: n_past = 172, truncated = 1
  1543. slot print_timing: id 10 | task 26722 |
  1544. prompt eval time = 503.29 ms / 199 tokens ( 2.53 ms per token, 395.40 tokens per second)
  1545. eval time = 16565.51 ms / 101 tokens ( 164.01 ms per token, 6.10 tokens per second)
  1546. total time = 17068.80 ms / 300 tokens
  1547. slot launch_slot_: id 10 | task 26821 | processing task
  1548. slot update_slots: id 10 | task 26821 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1549. slot update_slots: id 10 | task 26821 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1550. slot update_slots: id 10 | task 26821 | kv cache rm [0, end)
  1551. slot update_slots: id 10 | task 26821 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1552. slot update_slots: id 10 | task 26821 | prompt done, n_past = 199, n_tokens = 262
  1553. srv cancel_tasks: cancel task, id_task = 27625
  1554. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1555. srv params_from_: Chat format: Content-only
  1556. srv cancel_tasks: cancel task, id_task = 27590
  1557. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1558. srv params_from_: Chat format: Content-only
  1559. srv cancel_tasks: cancel task, id_task = 27595
  1560. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1561. srv params_from_: Chat format: Content-only
  1562. slot update_slots: id 9 | task 26740 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1563. slot update_slots: id 41 | task 26741 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1564. slot update_slots: id 52 | task 26742 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1565. slot release: id 41 | task 26741 | stop processing: n_past = 130, truncated = 1
  1566. slot print_timing: id 41 | task 26741 |
  1567. prompt eval time = 544.01 ms / 199 tokens ( 2.73 ms per token, 365.80 tokens per second)
  1568. eval time = 11285.63 ms / 59 tokens ( 191.28 ms per token, 5.23 tokens per second)
  1569. total time = 11829.64 ms / 258 tokens
  1570. slot launch_slot_: id 41 | task 26822 | processing task
  1571. slot update_slots: id 13 | task 26744 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1572. slot update_slots: id 18 | task 26745 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1573. slot update_slots: id 29 | task 26746 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1574. slot update_slots: id 50 | task 26747 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1575. slot update_slots: id 41 | task 26822 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1576. slot update_slots: id 41 | task 26822 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1577. slot update_slots: id 41 | task 26822 | kv cache rm [0, end)
  1578. slot update_slots: id 41 | task 26822 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1579. slot update_slots: id 41 | task 26822 | prompt done, n_past = 199, n_tokens = 262
  1580. slot release: id 9 | task 26740 | stop processing: n_past = 131, truncated = 1
  1581. slot print_timing: id 9 | task 26740 |
  1582. prompt eval time = 538.37 ms / 199 tokens ( 2.71 ms per token, 369.64 tokens per second)
  1583. eval time = 11459.73 ms / 60 tokens ( 191.00 ms per token, 5.24 tokens per second)
  1584. total time = 11998.10 ms / 259 tokens
  1585. slot launch_slot_: id 9 | task 26823 | processing task
  1586. slot update_slots: id 17 | task 26748 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1587. slot update_slots: id 9 | task 26823 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1588. slot update_slots: id 9 | task 26823 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1589. slot update_slots: id 9 | task 26823 | kv cache rm [0, end)
  1590. slot update_slots: id 9 | task 26823 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1591. slot update_slots: id 9 | task 26823 | prompt done, n_past = 199, n_tokens = 262
  1592. srv cancel_tasks: cancel task, id_task = 27627
  1593. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1594. srv params_from_: Chat format: Content-only
  1595. slot update_slots: id 40 | task 26750 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1596. slot update_slots: id 45 | task 26751 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1597. slot update_slots: id 57 | task 26752 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1598. slot release: id 13 | task 26744 | stop processing: n_past = 131, truncated = 1
  1599. slot print_timing: id 13 | task 26744 |
  1600. prompt eval time = 633.49 ms / 199 tokens ( 3.18 ms per token, 314.13 tokens per second)
  1601. eval time = 11182.17 ms / 60 tokens ( 186.37 ms per token, 5.37 tokens per second)
  1602. total time = 11815.66 ms / 259 tokens
  1603. slot launch_slot_: id 13 | task 26824 | processing task
  1604. slot update_slots: id 5 | task 26753 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1605. slot update_slots: id 63 | task 26754 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1606. slot update_slots: id 13 | task 26824 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1607. slot update_slots: id 13 | task 26824 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1608. slot update_slots: id 13 | task 26824 | kv cache rm [0, end)
  1609. slot update_slots: id 13 | task 26824 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1610. slot update_slots: id 13 | task 26824 | prompt done, n_past = 199, n_tokens = 262
  1611. slot release: id 17 | task 26748 | stop processing: n_past = 131, truncated = 1
  1612. slot print_timing: id 17 | task 26748 |
  1613. prompt eval time = 431.34 ms / 199 tokens ( 2.17 ms per token, 461.35 tokens per second)
  1614. eval time = 10907.48 ms / 60 tokens ( 181.79 ms per token, 5.50 tokens per second)
  1615. total time = 11338.82 ms / 259 tokens
  1616. slot launch_slot_: id 17 | task 26825 | processing task
  1617. slot update_slots: id 21 | task 26756 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1618. slot update_slots: id 58 | task 26757 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1619. slot update_slots: id 17 | task 26825 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1620. slot update_slots: id 17 | task 26825 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1621. slot update_slots: id 17 | task 26825 | kv cache rm [0, end)
  1622. slot update_slots: id 17 | task 26825 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1623. slot update_slots: id 17 | task 26825 | prompt done, n_past = 199, n_tokens = 262
  1624. slot release: id 5 | task 26753 | stop processing: n_past = 130, truncated = 1
  1625. slot print_timing: id 5 | task 26753 |
  1626. prompt eval time = 524.55 ms / 199 tokens ( 2.64 ms per token, 379.37 tokens per second)
  1627. eval time = 10184.43 ms / 59 tokens ( 172.62 ms per token, 5.79 tokens per second)
  1628. total time = 10708.98 ms / 258 tokens
  1629. slot release: id 40 | task 26750 | stop processing: n_past = 131, truncated = 1
  1630. slot print_timing: id 40 | task 26750 |
  1631. prompt eval time = 534.19 ms / 199 tokens ( 2.68 ms per token, 372.53 tokens per second)
  1632. eval time = 10716.53 ms / 60 tokens ( 178.61 ms per token, 5.60 tokens per second)
  1633. total time = 11250.72 ms / 259 tokens
  1634. slot release: id 45 | task 26751 | stop processing: n_past = 131, truncated = 1
  1635. slot print_timing: id 45 | task 26751 |
  1636. prompt eval time = 534.53 ms / 199 tokens ( 2.69 ms per token, 372.29 tokens per second)
  1637. eval time = 10716.60 ms / 60 tokens ( 178.61 ms per token, 5.60 tokens per second)
  1638. total time = 11251.13 ms / 259 tokens
  1639. slot launch_slot_: id 5 | task 26826 | processing task
  1640. slot launch_slot_: id 40 | task 26828 | processing task
  1641. slot launch_slot_: id 45 | task 26830 | processing task
  1642. slot update_slots: id 5 | task 26826 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1643. slot update_slots: id 5 | task 26826 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1644. slot update_slots: id 5 | task 26826 | kv cache rm [0, end)
  1645. slot update_slots: id 5 | task 26826 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  1646. slot update_slots: id 5 | task 26826 | prompt done, n_past = 199, n_tokens = 260
  1647. slot update_slots: id 40 | task 26828 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1648. slot update_slots: id 40 | task 26828 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1649. slot update_slots: id 40 | task 26828 | kv cache rm [0, end)
  1650. slot update_slots: id 40 | task 26828 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  1651. slot update_slots: id 40 | task 26828 | prompt done, n_past = 199, n_tokens = 459
  1652. slot update_slots: id 45 | task 26830 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1653. slot update_slots: id 45 | task 26830 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1654. slot update_slots: id 45 | task 26830 | kv cache rm [0, end)
  1655. slot update_slots: id 45 | task 26830 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  1656. slot update_slots: id 45 | task 26830 | prompt done, n_past = 199, n_tokens = 658
  1657. srv cancel_tasks: cancel task, id_task = 27622
  1658. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1659. srv cancel_tasks: cancel task, id_task = 27629
  1660. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  1661. srv params_from_: Chat format: Content-only
  1662. srv params_from_: Chat format: Content-only
  1663. slot release: id 1 | task 26701 | stop processing: n_past = 194, truncated = 1
  1664. slot print_timing: id 1 | task 26701 |
  1665. prompt eval time = 726.81 ms / 199 tokens ( 3.65 ms per token, 273.80 tokens per second)
  1666. eval time = 23519.38 ms / 123 tokens ( 191.21 ms per token, 5.23 tokens per second)
  1667. total time = 24246.19 ms / 322 tokens
  1668. slot release: id 58 | task 26757 | stop processing: n_past = 130, truncated = 1
  1669. slot print_timing: id 58 | task 26757 |
  1670. prompt eval time = 605.92 ms / 199 tokens ( 3.04 ms per token, 328.43 tokens per second)
  1671. eval time = 9930.10 ms / 59 tokens ( 168.31 ms per token, 5.94 tokens per second)
  1672. total time = 10536.02 ms / 258 tokens
  1673. slot launch_slot_: id 1 | task 27757 | processing task
  1674. slot launch_slot_: id 58 | task 27758 | processing task
  1675. slot update_slots: id 30 | task 26629 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1676. slot update_slots: id 60 | task 26758 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1677. slot update_slots: id 1 | task 27757 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1678. slot update_slots: id 1 | task 27757 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1679. slot update_slots: id 1 | task 27757 | kv cache rm [0, end)
  1680. slot update_slots: id 1 | task 27757 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1681. slot update_slots: id 1 | task 27757 | prompt done, n_past = 199, n_tokens = 261
  1682. slot update_slots: id 58 | task 27758 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1683. slot update_slots: id 58 | task 27758 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1684. slot update_slots: id 58 | task 27758 | kv cache rm [0, end)
  1685. slot update_slots: id 58 | task 27758 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1686. slot update_slots: id 58 | task 27758 | prompt done, n_past = 199, n_tokens = 460
  1687. slot release: id 21 | task 26756 | stop processing: n_past = 131, truncated = 1
  1688. slot print_timing: id 21 | task 26756 |
  1689. prompt eval time = 599.74 ms / 199 tokens ( 3.01 ms per token, 331.81 tokens per second)
  1690. eval time = 10383.83 ms / 60 tokens ( 173.06 ms per token, 5.78 tokens per second)
  1691. total time = 10983.57 ms / 259 tokens
  1692. slot launch_slot_: id 21 | task 26832 | processing task
  1693. slot update_slots: id 6 | task 26605 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1694. slot update_slots: id 21 | task 26832 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1695. slot update_slots: id 21 | task 26832 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1696. slot update_slots: id 21 | task 26832 | kv cache rm [0, end)
  1697. slot update_slots: id 21 | task 26832 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1698. slot update_slots: id 21 | task 26832 | prompt done, n_past = 199, n_tokens = 262
  1699. slot update_slots: id 51 | task 26761 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1700. slot release: id 60 | task 26758 | stop processing: n_past = 131, truncated = 1
  1701. slot print_timing: id 60 | task 26758 |
  1702. prompt eval time = 247.13 ms / 199 tokens ( 1.24 ms per token, 805.23 tokens per second)
  1703. eval time = 10366.95 ms / 60 tokens ( 172.78 ms per token, 5.79 tokens per second)
  1704. total time = 10614.08 ms / 259 tokens
  1705. slot launch_slot_: id 60 | task 26836 | processing task
  1706. slot update_slots: id 43 | task 26653 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1707. slot update_slots: id 60 | task 26836 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1708. slot update_slots: id 60 | task 26836 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1709. slot update_slots: id 60 | task 26836 | kv cache rm [0, end)
  1710. slot update_slots: id 60 | task 26836 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1711. slot update_slots: id 60 | task 26836 | prompt done, n_past = 199, n_tokens = 262
  1712. slot release: id 51 | task 26761 | stop processing: n_past = 131, truncated = 1
  1713. slot print_timing: id 51 | task 26761 |
  1714. prompt eval time = 59.29 ms / 1 tokens ( 59.29 ms per token, 16.87 tokens per second)
  1715. eval time = 10358.93 ms / 60 tokens ( 172.65 ms per token, 5.79 tokens per second)
  1716. total time = 10418.22 ms / 61 tokens
  1717. slot launch_slot_: id 51 | task 26837 | processing task
  1718. slot update_slots: id 51 | task 26837 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1719. slot update_slots: id 51 | task 26837 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1720. slot update_slots: id 51 | task 26837 | kv cache rm [0, end)
  1721. slot update_slots: id 51 | task 26837 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1722. slot update_slots: id 51 | task 26837 | prompt done, n_past = 199, n_tokens = 262
  1723. slot update_slots: id 3 | task 26762 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1724. slot update_slots: id 20 | task 26763 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1725. slot update_slots: id 26 | task 26764 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1726. slot update_slots: id 32 | task 26767 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1727. slot update_slots: id 47 | task 26768 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1728. slot release: id 32 | task 26767 | stop processing: n_past = 130, truncated = 1
  1729. slot print_timing: id 32 | task 26767 |
  1730. prompt eval time = 541.59 ms / 199 tokens ( 2.72 ms per token, 367.44 tokens per second)
  1731. eval time = 9906.24 ms / 59 tokens ( 167.90 ms per token, 5.96 tokens per second)
  1732. total time = 10447.83 ms / 258 tokens
  1733. slot launch_slot_: id 32 | task 26846 | processing task
  1734. slot update_slots: id 19 | task 26483 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1735. slot update_slots: id 22 | task 26488 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1736. slot update_slots: id 23 | task 26535 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1737. slot update_slots: id 25 | task 26512 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1738. slot update_slots: id 35 | task 26522 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1739. slot update_slots: id 37 | task 26484 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1740. slot update_slots: id 46 | task 26775 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1741. slot update_slots: id 32 | task 26846 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1742. slot update_slots: id 32 | task 26846 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1743. slot update_slots: id 32 | task 26846 | kv cache rm [0, end)
  1744. slot update_slots: id 32 | task 26846 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1745. slot update_slots: id 32 | task 26846 | prompt done, n_past = 199, n_tokens = 262
  1746. slot release: id 20 | task 26763 | stop processing: n_past = 131, truncated = 1
  1747. slot print_timing: id 20 | task 26763 |
  1748. prompt eval time = 539.61 ms / 199 tokens ( 2.71 ms per token, 368.78 tokens per second)
  1749. eval time = 10380.00 ms / 60 tokens ( 173.00 ms per token, 5.78 tokens per second)
  1750. total time = 10919.61 ms / 259 tokens
  1751. slot release: id 26 | task 26764 | stop processing: n_past = 131, truncated = 1
  1752. slot print_timing: id 26 | task 26764 |
  1753. prompt eval time = 540.12 ms / 199 tokens ( 2.71 ms per token, 368.43 tokens per second)
  1754. eval time = 10379.93 ms / 60 tokens ( 173.00 ms per token, 5.78 tokens per second)
  1755. total time = 10920.06 ms / 259 tokens
  1756. slot release: id 47 | task 26768 | stop processing: n_past = 131, truncated = 1
  1757. slot print_timing: id 47 | task 26768 |
  1758. prompt eval time = 544.09 ms / 199 tokens ( 2.73 ms per token, 365.75 tokens per second)
  1759. eval time = 10377.65 ms / 60 tokens ( 172.96 ms per token, 5.78 tokens per second)
  1760. total time = 10921.74 ms / 259 tokens
  1761. slot launch_slot_: id 20 | task 26848 | processing task
  1762. slot launch_slot_: id 26 | task 26849 | processing task
  1763. slot launch_slot_: id 47 | task 26852 | processing task
  1764. slot update_slots: id 48 | task 26498 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1765. slot update_slots: id 53 | task 26776 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1766. slot update_slots: id 54 | task 26525 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1767. slot update_slots: id 20 | task 26848 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1768. slot update_slots: id 20 | task 26848 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1769. slot update_slots: id 20 | task 26848 | kv cache rm [0, end)
  1770. slot update_slots: id 20 | task 26848 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  1771. slot update_slots: id 20 | task 26848 | prompt done, n_past = 199, n_tokens = 260
  1772. slot update_slots: id 26 | task 26849 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1773. slot update_slots: id 26 | task 26849 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1774. slot update_slots: id 26 | task 26849 | kv cache rm [0, end)
  1775. slot update_slots: id 26 | task 26849 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  1776. slot update_slots: id 26 | task 26849 | prompt done, n_past = 199, n_tokens = 459
  1777. slot update_slots: id 47 | task 26852 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1778. slot update_slots: id 47 | task 26852 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1779. slot update_slots: id 47 | task 26852 | kv cache rm [0, end)
  1780. slot update_slots: id 47 | task 26852 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  1781. slot update_slots: id 47 | task 26852 | prompt done, n_past = 199, n_tokens = 658
  1782. slot update_slots: id 59 | task 26787 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1783. slot update_slots: id 33 | task 26790 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1784. slot update_slots: id 42 | task 26789 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1785. slot release: id 33 | task 26790 | stop processing: n_past = 131, truncated = 1
  1786. slot print_timing: id 33 | task 26790 |
  1787. prompt eval time = 161.81 ms / 1 tokens ( 161.81 ms per token, 6.18 tokens per second)
  1788. eval time = 10230.82 ms / 60 tokens ( 170.51 ms per token, 5.86 tokens per second)
  1789. total time = 10392.62 ms / 61 tokens
  1790. slot launch_slot_: id 33 | task 26851 | processing task
  1791. slot update_slots: id 33 | task 26851 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1792. slot update_slots: id 33 | task 26851 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1793. slot update_slots: id 33 | task 26851 | kv cache rm [0, end)
  1794. slot update_slots: id 33 | task 26851 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1795. slot update_slots: id 33 | task 26851 | prompt done, n_past = 199, n_tokens = 262
  1796. slot update_slots: id 27 | task 26791 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1797. slot release: id 27 | task 26791 | stop processing: n_past = 130, truncated = 1
  1798. slot print_timing: id 27 | task 26791 |
  1799. prompt eval time = 56.54 ms / 1 tokens ( 56.54 ms per token, 17.69 tokens per second)
  1800. eval time = 10255.18 ms / 59 tokens ( 173.82 ms per token, 5.75 tokens per second)
  1801. total time = 10311.72 ms / 60 tokens
  1802. slot launch_slot_: id 27 | task 26856 | processing task
  1803. slot update_slots: id 27 | task 26856 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1804. slot update_slots: id 27 | task 26856 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1805. slot update_slots: id 27 | task 26856 | kv cache rm [0, end)
  1806. slot update_slots: id 27 | task 26856 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1807. slot update_slots: id 27 | task 26856 | prompt done, n_past = 199, n_tokens = 262
  1808. slot update_slots: id 4 | task 26792 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1809. slot update_slots: id 12 | task 26793 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1810. slot update_slots: id 15 | task 26795 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1811. slot update_slots: id 7 | task 26802 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1812. slot update_slots: id 39 | task 26805 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1813. slot release: id 12 | task 26793 | stop processing: n_past = 131, truncated = 1
  1814. slot print_timing: id 12 | task 26793 |
  1815. prompt eval time = 165.31 ms / 1 tokens ( 165.31 ms per token, 6.05 tokens per second)
  1816. eval time = 10135.12 ms / 60 tokens ( 168.92 ms per token, 5.92 tokens per second)
  1817. total time = 10300.43 ms / 61 tokens
  1818. slot launch_slot_: id 12 | task 26858 | processing task
  1819. slot update_slots: id 2 | task 26807 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1820. slot update_slots: id 12 | task 26858 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1821. slot update_slots: id 12 | task 26858 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1822. slot update_slots: id 12 | task 26858 | kv cache rm [0, end)
  1823. slot update_slots: id 12 | task 26858 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1824. slot update_slots: id 12 | task 26858 | prompt done, n_past = 199, n_tokens = 262
  1825. slot update_slots: id 11 | task 26813 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1826. slot release: id 7 | task 26802 | stop processing: n_past = 131, truncated = 1
  1827. slot print_timing: id 7 | task 26802 |
  1828. prompt eval time = 248.14 ms / 199 tokens ( 1.25 ms per token, 801.97 tokens per second)
  1829. eval time = 10207.34 ms / 60 tokens ( 170.12 ms per token, 5.88 tokens per second)
  1830. total time = 10455.48 ms / 259 tokens
  1831. slot release: id 39 | task 26805 | stop processing: n_past = 131, truncated = 1
  1832. slot print_timing: id 39 | task 26805 |
  1833. prompt eval time = 250.74 ms / 199 tokens ( 1.26 ms per token, 793.65 tokens per second)
  1834. eval time = 10207.58 ms / 60 tokens ( 170.13 ms per token, 5.88 tokens per second)
  1835. total time = 10458.32 ms / 259 tokens
  1836. slot launch_slot_: id 7 | task 26860 | processing task
  1837. slot launch_slot_: id 39 | task 26861 | processing task
  1838. slot update_slots: id 34 | task 26816 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1839. slot update_slots: id 7 | task 26860 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1840. slot update_slots: id 7 | task 26860 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1841. slot update_slots: id 7 | task 26860 | kv cache rm [0, end)
  1842. slot update_slots: id 7 | task 26860 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1843. slot update_slots: id 7 | task 26860 | prompt done, n_past = 199, n_tokens = 261
  1844. slot update_slots: id 39 | task 26861 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1845. slot update_slots: id 39 | task 26861 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1846. slot update_slots: id 39 | task 26861 | kv cache rm [0, end)
  1847. slot update_slots: id 39 | task 26861 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1848. slot update_slots: id 39 | task 26861 | prompt done, n_past = 199, n_tokens = 460
  1849. slot release: id 2 | task 26807 | stop processing: n_past = 131, truncated = 1
  1850. slot print_timing: id 2 | task 26807 |
  1851. prompt eval time = 236.85 ms / 1 tokens ( 236.85 ms per token, 4.22 tokens per second)
  1852. eval time = 10202.90 ms / 60 tokens ( 170.05 ms per token, 5.88 tokens per second)
  1853. total time = 10439.76 ms / 61 tokens
  1854. slot launch_slot_: id 2 | task 26864 | processing task
  1855. slot update_slots: id 31 | task 26818 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1856. slot update_slots: id 36 | task 26819 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1857. slot update_slots: id 2 | task 26864 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1858. slot update_slots: id 2 | task 26864 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1859. slot update_slots: id 2 | task 26864 | kv cache rm [0, end)
  1860. slot update_slots: id 2 | task 26864 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1861. slot update_slots: id 2 | task 26864 | prompt done, n_past = 199, n_tokens = 262
  1862. slot release: id 29 | task 26746 | stop processing: n_past = 172, truncated = 1
  1863. slot print_timing: id 29 | task 26746 |
  1864. prompt eval time = 636.64 ms / 199 tokens ( 3.20 ms per token, 312.58 tokens per second)
  1865. eval time = 18418.51 ms / 101 tokens ( 182.36 ms per token, 5.48 tokens per second)
  1866. total time = 19055.15 ms / 300 tokens
  1867. slot release: id 50 | task 26747 | stop processing: n_past = 172, truncated = 1
  1868. slot print_timing: id 50 | task 26747 |
  1869. prompt eval time = 639.59 ms / 199 tokens ( 3.21 ms per token, 311.14 tokens per second)
  1870. eval time = 18417.18 ms / 101 tokens ( 182.35 ms per token, 5.48 tokens per second)
  1871. total time = 19056.77 ms / 300 tokens
  1872. slot launch_slot_: id 29 | task 26865 | processing task
  1873. slot launch_slot_: id 50 | task 26866 | processing task
  1874. slot update_slots: id 29 | task 26865 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1875. slot update_slots: id 29 | task 26865 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1876. slot update_slots: id 29 | task 26865 | kv cache rm [0, end)
  1877. slot update_slots: id 29 | task 26865 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1878. slot update_slots: id 29 | task 26865 | prompt done, n_past = 199, n_tokens = 261
  1879. slot update_slots: id 50 | task 26866 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1880. slot update_slots: id 50 | task 26866 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1881. slot update_slots: id 50 | task 26866 | kv cache rm [0, end)
  1882. slot update_slots: id 50 | task 26866 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1883. slot update_slots: id 50 | task 26866 | prompt done, n_past = 199, n_tokens = 460
  1884. slot release: id 34 | task 26816 | stop processing: n_past = 131, truncated = 1
  1885. slot print_timing: id 34 | task 26816 |
  1886. prompt eval time = 159.12 ms / 199 tokens ( 0.80 ms per token, 1250.60 tokens per second)
  1887. eval time = 10167.10 ms / 60 tokens ( 169.45 ms per token, 5.90 tokens per second)
  1888. total time = 10326.22 ms / 259 tokens
  1889. slot launch_slot_: id 34 | task 26867 | processing task
  1890. slot update_slots: id 34 | task 26867 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1891. slot update_slots: id 34 | task 26867 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1892. slot update_slots: id 34 | task 26867 | kv cache rm [0, end)
  1893. slot update_slots: id 34 | task 26867 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1894. slot update_slots: id 34 | task 26867 | prompt done, n_past = 199, n_tokens = 262
  1895. slot release: id 31 | task 26818 | stop processing: n_past = 131, truncated = 1
  1896. slot print_timing: id 31 | task 26818 |
  1897. prompt eval time = 249.69 ms / 199 tokens ( 1.25 ms per token, 796.99 tokens per second)
  1898. eval time = 10241.27 ms / 60 tokens ( 170.69 ms per token, 5.86 tokens per second)
  1899. total time = 10490.96 ms / 259 tokens
  1900. slot release: id 36 | task 26819 | stop processing: n_past = 131, truncated = 1
  1901. slot print_timing: id 36 | task 26819 |
  1902. prompt eval time = 250.02 ms / 199 tokens ( 1.26 ms per token, 795.93 tokens per second)
  1903. eval time = 10241.29 ms / 60 tokens ( 170.69 ms per token, 5.86 tokens per second)
  1904. total time = 10491.31 ms / 259 tokens
  1905. slot launch_slot_: id 31 | task 26868 | processing task
  1906. slot launch_slot_: id 36 | task 26869 | processing task
  1907. slot update_slots: id 55 | task 26686 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1908. slot update_slots: id 31 | task 26868 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1909. slot update_slots: id 31 | task 26868 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1910. slot update_slots: id 31 | task 26868 | kv cache rm [0, end)
  1911. slot update_slots: id 31 | task 26868 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  1912. slot update_slots: id 31 | task 26868 | prompt done, n_past = 199, n_tokens = 261
  1913. slot update_slots: id 36 | task 26869 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1914. slot update_slots: id 36 | task 26869 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1915. slot update_slots: id 36 | task 26869 | kv cache rm [0, end)
  1916. slot update_slots: id 36 | task 26869 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  1917. slot update_slots: id 36 | task 26869 | prompt done, n_past = 199, n_tokens = 460
  1918. slot release: id 63 | task 26754 | stop processing: n_past = 172, truncated = 1
  1919. slot print_timing: id 63 | task 26754 |
  1920. prompt eval time = 536.53 ms / 199 tokens ( 2.70 ms per token, 370.90 tokens per second)
  1921. eval time = 17874.61 ms / 101 tokens ( 176.98 ms per token, 5.65 tokens per second)
  1922. total time = 18411.14 ms / 300 tokens
  1923. slot launch_slot_: id 63 | task 26871 | processing task
  1924. slot update_slots: id 63 | task 26871 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1925. slot update_slots: id 63 | task 26871 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1926. slot update_slots: id 63 | task 26871 | kv cache rm [0, end)
  1927. slot update_slots: id 63 | task 26871 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1928. slot update_slots: id 63 | task 26871 | prompt done, n_past = 199, n_tokens = 262
  1929. slot release: id 28 | task 26735 | stop processing: n_past = 194, truncated = 1
  1930. slot print_timing: id 28 | task 26735 |
  1931. prompt eval time = 244.64 ms / 199 tokens ( 1.23 ms per token, 813.44 tokens per second)
  1932. eval time = 23122.17 ms / 123 tokens ( 187.99 ms per token, 5.32 tokens per second)
  1933. total time = 23366.81 ms / 322 tokens
  1934. slot launch_slot_: id 28 | task 26872 | processing task
  1935. slot update_slots: id 28 | task 26872 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1936. slot update_slots: id 28 | task 26872 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1937. slot update_slots: id 28 | task 26872 | kv cache rm [0, end)
  1938. slot update_slots: id 28 | task 26872 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1939. slot update_slots: id 28 | task 26872 | prompt done, n_past = 199, n_tokens = 262
  1940. slot release: id 56 | task 26737 | stop processing: n_past = 195, truncated = 1
  1941. slot print_timing: id 56 | task 26737 |
  1942. prompt eval time = 252.44 ms / 199 tokens ( 1.27 ms per token, 788.32 tokens per second)
  1943. eval time = 22977.14 ms / 124 tokens ( 185.30 ms per token, 5.40 tokens per second)
  1944. total time = 23229.58 ms / 323 tokens
  1945. slot launch_slot_: id 56 | task 26873 | processing task
  1946. slot update_slots: id 56 | task 26873 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1947. slot update_slots: id 56 | task 26873 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1948. slot update_slots: id 56 | task 26873 | kv cache rm [0, end)
  1949. slot update_slots: id 56 | task 26873 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1950. slot update_slots: id 56 | task 26873 | prompt done, n_past = 199, n_tokens = 262
  1951. slot update_slots: id 10 | task 26821 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1952. slot release: id 8 | task 26734 | stop processing: n_past = 203, truncated = 1
  1953. slot print_timing: id 8 | task 26734 |
  1954. prompt eval time = 241.38 ms / 199 tokens ( 1.21 ms per token, 824.44 tokens per second)
  1955. eval time = 24013.20 ms / 132 tokens ( 181.92 ms per token, 5.50 tokens per second)
  1956. total time = 24254.58 ms / 331 tokens
  1957. slot launch_slot_: id 8 | task 26875 | processing task
  1958. slot update_slots: id 41 | task 26822 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1959. slot update_slots: id 8 | task 26875 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1960. slot update_slots: id 8 | task 26875 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1961. slot update_slots: id 8 | task 26875 | kv cache rm [0, end)
  1962. slot update_slots: id 8 | task 26875 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1963. slot update_slots: id 8 | task 26875 | prompt done, n_past = 199, n_tokens = 262
  1964. slot update_slots: id 9 | task 26823 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1965. slot release: id 41 | task 26822 | stop processing: n_past = 131, truncated = 1
  1966. slot print_timing: id 41 | task 26822 |
  1967. prompt eval time = 168.95 ms / 199 tokens ( 0.85 ms per token, 1177.84 tokens per second)
  1968. eval time = 10599.87 ms / 60 tokens ( 176.66 ms per token, 5.66 tokens per second)
  1969. total time = 10768.82 ms / 259 tokens
  1970. slot launch_slot_: id 41 | task 26876 | processing task
  1971. slot update_slots: id 13 | task 26824 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1972. slot update_slots: id 41 | task 26876 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1973. slot update_slots: id 41 | task 26876 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1974. slot update_slots: id 41 | task 26876 | kv cache rm [0, end)
  1975. slot update_slots: id 41 | task 26876 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1976. slot update_slots: id 41 | task 26876 | prompt done, n_past = 199, n_tokens = 262
  1977. slot update_slots: id 17 | task 26825 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1978. slot update_slots: id 5 | task 26826 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1979. slot update_slots: id 40 | task 26828 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1980. slot update_slots: id 45 | task 26830 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1981. slot release: id 13 | task 26824 | stop processing: n_past = 131, truncated = 1
  1982. slot print_timing: id 13 | task 26824 |
  1983. prompt eval time = 161.46 ms / 199 tokens ( 0.81 ms per token, 1232.51 tokens per second)
  1984. eval time = 10181.48 ms / 60 tokens ( 169.69 ms per token, 5.89 tokens per second)
  1985. total time = 10342.94 ms / 259 tokens
  1986. slot launch_slot_: id 13 | task 26877 | processing task
  1987. slot update_slots: id 1 | task 27757 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1988. slot update_slots: id 58 | task 27758 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  1989. slot update_slots: id 13 | task 26877 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  1990. slot update_slots: id 13 | task 26877 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  1991. slot update_slots: id 13 | task 26877 | kv cache rm [0, end)
  1992. slot update_slots: id 13 | task 26877 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  1993. slot update_slots: id 13 | task 26877 | prompt done, n_past = 199, n_tokens = 262
  1994. slot release: id 17 | task 26825 | stop processing: n_past = 131, truncated = 1
  1995. slot print_timing: id 17 | task 26825 |
  1996. prompt eval time = 346.39 ms / 199 tokens ( 1.74 ms per token, 574.50 tokens per second)
  1997. eval time = 10169.69 ms / 60 tokens ( 169.49 ms per token, 5.90 tokens per second)
  1998. total time = 10516.08 ms / 259 tokens
  1999. slot release: id 45 | task 26830 | stop processing: n_past = 130, truncated = 1
  2000. slot print_timing: id 45 | task 26830 |
  2001. prompt eval time = 357.28 ms / 199 tokens ( 1.80 ms per token, 556.98 tokens per second)
  2002. eval time = 9810.61 ms / 59 tokens ( 166.28 ms per token, 6.01 tokens per second)
  2003. total time = 10167.89 ms / 258 tokens
  2004. slot launch_slot_: id 17 | task 26878 | processing task
  2005. slot launch_slot_: id 45 | task 26879 | processing task
  2006. slot update_slots: id 21 | task 26832 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2007. slot update_slots: id 17 | task 26878 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2008. slot update_slots: id 17 | task 26878 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2009. slot update_slots: id 17 | task 26878 | kv cache rm [0, end)
  2010. slot update_slots: id 17 | task 26878 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2011. slot update_slots: id 17 | task 26878 | prompt done, n_past = 199, n_tokens = 261
  2012. slot update_slots: id 45 | task 26879 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2013. slot update_slots: id 45 | task 26879 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2014. slot update_slots: id 45 | task 26879 | kv cache rm [0, end)
  2015. slot update_slots: id 45 | task 26879 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2016. slot update_slots: id 45 | task 26879 | prompt done, n_past = 199, n_tokens = 460
  2017. slot release: id 5 | task 26826 | stop processing: n_past = 131, truncated = 1
  2018. slot print_timing: id 5 | task 26826 |
  2019. prompt eval time = 354.16 ms / 199 tokens ( 1.78 ms per token, 561.89 tokens per second)
  2020. eval time = 10224.60 ms / 60 tokens ( 170.41 ms per token, 5.87 tokens per second)
  2021. total time = 10578.77 ms / 259 tokens
  2022. slot release: id 40 | task 26828 | stop processing: n_past = 131, truncated = 1
  2023. slot print_timing: id 40 | task 26828 |
  2024. prompt eval time = 356.95 ms / 199 tokens ( 1.79 ms per token, 557.50 tokens per second)
  2025. eval time = 10224.69 ms / 60 tokens ( 170.41 ms per token, 5.87 tokens per second)
  2026. total time = 10581.64 ms / 259 tokens
  2027. slot launch_slot_: id 5 | task 26880 | processing task
  2028. slot launch_slot_: id 40 | task 26882 | processing task
  2029. slot update_slots: id 5 | task 26880 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2030. slot update_slots: id 5 | task 26880 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2031. slot update_slots: id 5 | task 26880 | kv cache rm [0, end)
  2032. slot update_slots: id 5 | task 26880 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2033. slot update_slots: id 5 | task 26880 | prompt done, n_past = 199, n_tokens = 261
  2034. slot update_slots: id 40 | task 26882 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2035. slot update_slots: id 40 | task 26882 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2036. slot update_slots: id 40 | task 26882 | kv cache rm [0, end)
  2037. slot update_slots: id 40 | task 26882 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2038. slot update_slots: id 40 | task 26882 | prompt done, n_past = 199, n_tokens = 460
  2039. slot release: id 1 | task 27757 | stop processing: n_past = 131, truncated = 1
  2040. slot print_timing: id 1 | task 27757 |
  2041. prompt eval time = 443.84 ms / 199 tokens ( 2.23 ms per token, 448.36 tokens per second)
  2042. eval time = 10318.12 ms / 60 tokens ( 171.97 ms per token, 5.82 tokens per second)
  2043. total time = 10761.96 ms / 259 tokens
  2044. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2045. slot release: id 18 | task 26745 | stop processing: n_past = 194, truncated = 1
  2046. slot print_timing: id 18 | task 26745 |
  2047. prompt eval time = 634.00 ms / 199 tokens ( 3.19 ms per token, 313.88 tokens per second)
  2048. eval time = 22825.55 ms / 123 tokens ( 185.57 ms per token, 5.39 tokens per second)
  2049. total time = 23459.55 ms / 322 tokens
  2050. srv params_from_: Chat format: Content-only
  2051. slot launch_slot_: id 1 | task 26884 | processing task
  2052. slot launch_slot_: id 18 | task 26885 | processing task
  2053. slot update_slots: id 60 | task 26836 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2054. slot update_slots: id 1 | task 26884 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2055. slot update_slots: id 1 | task 26884 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2056. slot update_slots: id 1 | task 26884 | kv cache rm [0, end)
  2057. slot update_slots: id 1 | task 26884 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2058. slot update_slots: id 1 | task 26884 | prompt done, n_past = 199, n_tokens = 261
  2059. slot update_slots: id 18 | task 26885 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2060. slot update_slots: id 18 | task 26885 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2061. slot update_slots: id 18 | task 26885 | kv cache rm [0, end)
  2062. slot update_slots: id 18 | task 26885 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2063. slot update_slots: id 18 | task 26885 | prompt done, n_past = 199, n_tokens = 460
  2064. slot release: id 21 | task 26832 | stop processing: n_past = 131, truncated = 1
  2065. slot print_timing: id 21 | task 26832 |
  2066. prompt eval time = 345.33 ms / 199 tokens ( 1.74 ms per token, 576.25 tokens per second)
  2067. eval time = 10431.18 ms / 60 tokens ( 173.85 ms per token, 5.75 tokens per second)
  2068. total time = 10776.51 ms / 259 tokens
  2069. slot launch_slot_: id 21 | task 26886 | processing task
  2070. slot update_slots: id 0 | task 26700 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2071. slot update_slots: id 21 | task 26886 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2072. slot update_slots: id 21 | task 26886 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2073. slot update_slots: id 21 | task 26886 | kv cache rm [0, end)
  2074. slot update_slots: id 21 | task 26886 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2075. slot update_slots: id 21 | task 26886 | prompt done, n_past = 199, n_tokens = 262
  2076. slot update_slots: id 51 | task 26837 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2077. slot release: id 42 | task 26789 | stop processing: n_past = 172, truncated = 1
  2078. slot print_timing: id 42 | task 26789 |
  2079. prompt eval time = 162.49 ms / 199 tokens ( 0.82 ms per token, 1224.70 tokens per second)
  2080. eval time = 17704.47 ms / 101 tokens ( 175.29 ms per token, 5.70 tokens per second)
  2081. total time = 17866.96 ms / 300 tokens
  2082. slot release: id 60 | task 26836 | stop processing: n_past = 131, truncated = 1
  2083. slot print_timing: id 60 | task 26836 |
  2084. prompt eval time = 352.17 ms / 199 tokens ( 1.77 ms per token, 565.06 tokens per second)
  2085. eval time = 10433.90 ms / 60 tokens ( 173.90 ms per token, 5.75 tokens per second)
  2086. total time = 10786.07 ms / 259 tokens
  2087. slot launch_slot_: id 42 | task 26888 | processing task
  2088. slot launch_slot_: id 60 | task 26889 | processing task
  2089. slot update_slots: id 42 | task 26888 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2090. slot update_slots: id 42 | task 26888 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2091. slot update_slots: id 42 | task 26888 | kv cache rm [0, end)
  2092. slot update_slots: id 42 | task 26888 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2093. slot update_slots: id 42 | task 26888 | prompt done, n_past = 199, n_tokens = 261
  2094. slot update_slots: id 60 | task 26889 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2095. slot update_slots: id 60 | task 26889 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2096. slot update_slots: id 60 | task 26889 | kv cache rm [0, end)
  2097. slot update_slots: id 60 | task 26889 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2098. slot update_slots: id 60 | task 26889 | prompt done, n_past = 199, n_tokens = 460
  2099. slot release: id 51 | task 26837 | stop processing: n_past = 130, truncated = 1
  2100. slot print_timing: id 51 | task 26837 |
  2101. prompt eval time = 159.91 ms / 199 tokens ( 0.80 ms per token, 1244.42 tokens per second)
  2102. eval time = 10455.91 ms / 59 tokens ( 177.22 ms per token, 5.64 tokens per second)
  2103. total time = 10615.83 ms / 258 tokens
  2104. slot launch_slot_: id 51 | task 26891 | processing task
  2105. slot update_slots: id 49 | task 26713 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2106. slot update_slots: id 61 | task 26715 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2107. slot update_slots: id 51 | task 26891 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2108. slot update_slots: id 51 | task 26891 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2109. slot update_slots: id 51 | task 26891 | kv cache rm [0, end)
  2110. slot update_slots: id 51 | task 26891 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2111. slot update_slots: id 51 | task 26891 | prompt done, n_past = 199, n_tokens = 262
  2112. slot update_slots: id 32 | task 26846 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2113. slot update_slots: id 20 | task 26848 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2114. slot update_slots: id 26 | task 26849 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2115. slot update_slots: id 47 | task 26852 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2116. slot release: id 26 | task 26849 | stop processing: n_past = 131, truncated = 1
  2117. slot print_timing: id 26 | task 26849 |
  2118. prompt eval time = 573.56 ms / 199 tokens ( 2.88 ms per token, 346.96 tokens per second)
  2119. eval time = 9925.78 ms / 60 tokens ( 165.43 ms per token, 6.04 tokens per second)
  2120. total time = 10499.34 ms / 259 tokens
  2121. slot launch_slot_: id 26 | task 26892 | processing task
  2122. slot update_slots: id 16 | task 26582 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2123. slot update_slots: id 26 | task 26892 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2124. slot update_slots: id 26 | task 26892 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2125. slot update_slots: id 26 | task 26892 | kv cache rm [0, end)
  2126. slot update_slots: id 26 | task 26892 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2127. slot update_slots: id 26 | task 26892 | prompt done, n_past = 199, n_tokens = 262
  2128. slot update_slots: id 38 | task 26598 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2129. slot update_slots: id 44 | task 26608 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2130. slot update_slots: id 62 | task 26614 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2131. slot release: id 3 | task 26762 | stop processing: n_past = 194, truncated = 1
  2132. slot print_timing: id 3 | task 26762 |
  2133. prompt eval time = 536.72 ms / 199 tokens ( 2.70 ms per token, 370.77 tokens per second)
  2134. eval time = 21336.96 ms / 123 tokens ( 173.47 ms per token, 5.76 tokens per second)
  2135. total time = 21873.69 ms / 322 tokens
  2136. slot launch_slot_: id 3 | task 26893 | processing task
  2137. slot update_slots: id 3 | task 26893 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2138. slot update_slots: id 3 | task 26893 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2139. slot update_slots: id 3 | task 26893 | kv cache rm [0, end)
  2140. slot update_slots: id 3 | task 26893 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2141. slot update_slots: id 3 | task 26893 | prompt done, n_past = 199, n_tokens = 262
  2142. slot update_slots: id 33 | task 26851 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2143. slot release: id 59 | task 26787 | stop processing: n_past = 194, truncated = 1
  2144. slot print_timing: id 59 | task 26787 |
  2145. prompt eval time = 161.62 ms / 199 tokens ( 0.81 ms per token, 1231.28 tokens per second)
  2146. eval time = 20404.29 ms / 123 tokens ( 165.89 ms per token, 6.03 tokens per second)
  2147. total time = 20565.91 ms / 322 tokens
  2148. slot launch_slot_: id 59 | task 26894 | processing task
  2149. slot update_slots: id 59 | task 26894 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2150. slot update_slots: id 59 | task 26894 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2151. slot update_slots: id 59 | task 26894 | kv cache rm [0, end)
  2152. slot update_slots: id 59 | task 26894 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2153. slot update_slots: id 59 | task 26894 | prompt done, n_past = 199, n_tokens = 262
  2154. slot release: id 46 | task 26775 | stop processing: n_past = 203, truncated = 1
  2155. slot print_timing: id 46 | task 26775 |
  2156. prompt eval time = 514.00 ms / 199 tokens ( 2.58 ms per token, 387.16 tokens per second)
  2157. eval time = 21401.80 ms / 132 tokens ( 162.13 ms per token, 6.17 tokens per second)
  2158. total time = 21915.80 ms / 331 tokens
  2159. slot launch_slot_: id 46 | task 26895 | processing task
  2160. slot update_slots: id 46 | task 26895 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2161. slot update_slots: id 46 | task 26895 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2162. slot update_slots: id 46 | task 26895 | kv cache rm [0, end)
  2163. slot update_slots: id 46 | task 26895 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2164. slot update_slots: id 46 | task 26895 | prompt done, n_past = 199, n_tokens = 262
  2165. slot update_slots: id 27 | task 26856 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2166. slot release: id 27 | task 26856 | stop processing: n_past = 131, truncated = 1
  2167. slot print_timing: id 27 | task 26856 |
  2168. prompt eval time = 153.74 ms / 199 tokens ( 0.77 ms per token, 1294.42 tokens per second)
  2169. eval time = 9996.21 ms / 60 tokens ( 166.60 ms per token, 6.00 tokens per second)
  2170. total time = 10149.95 ms / 259 tokens
  2171. slot launch_slot_: id 27 | task 26896 | processing task
  2172. slot update_slots: id 27 | task 26896 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2173. slot update_slots: id 27 | task 26896 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2174. slot update_slots: id 27 | task 26896 | kv cache rm [0, end)
  2175. slot update_slots: id 27 | task 26896 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2176. slot update_slots: id 27 | task 26896 | prompt done, n_past = 199, n_tokens = 262
  2177. slot update_slots: id 12 | task 26858 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2178. slot update_slots: id 7 | task 26860 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2179. slot update_slots: id 39 | task 26861 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2180. slot release: id 12 | task 26858 | stop processing: n_past = 131, truncated = 1
  2181. slot print_timing: id 12 | task 26858 |
  2182. prompt eval time = 323.25 ms / 199 tokens ( 1.62 ms per token, 615.62 tokens per second)
  2183. eval time = 9654.51 ms / 60 tokens ( 160.91 ms per token, 6.21 tokens per second)
  2184. total time = 9977.77 ms / 259 tokens
  2185. slot launch_slot_: id 12 | task 26897 | processing task
  2186. slot update_slots: id 2 | task 26864 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2187. slot update_slots: id 12 | task 26897 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2188. slot update_slots: id 12 | task 26897 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2189. slot update_slots: id 12 | task 26897 | kv cache rm [0, end)
  2190. slot update_slots: id 12 | task 26897 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2191. slot update_slots: id 12 | task 26897 | prompt done, n_past = 199, n_tokens = 262
  2192. slot update_slots: id 29 | task 26865 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2193. slot update_slots: id 50 | task 26866 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2194. slot release: id 7 | task 26860 | stop processing: n_past = 131, truncated = 1
  2195. slot print_timing: id 7 | task 26860 |
  2196. prompt eval time = 231.43 ms / 199 tokens ( 1.16 ms per token, 859.86 tokens per second)
  2197. eval time = 9579.62 ms / 60 tokens ( 159.66 ms per token, 6.26 tokens per second)
  2198. total time = 9811.05 ms / 259 tokens
  2199. slot launch_slot_: id 7 | task 26898 | processing task
  2200. slot update_slots: id 34 | task 26867 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2201. slot update_slots: id 7 | task 26898 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2202. slot update_slots: id 7 | task 26898 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2203. slot update_slots: id 7 | task 26898 | kv cache rm [0, end)
  2204. slot update_slots: id 7 | task 26898 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2205. slot update_slots: id 7 | task 26898 | prompt done, n_past = 199, n_tokens = 262
  2206. slot update_slots: id 31 | task 26868 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2207. slot update_slots: id 36 | task 26869 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2208. slot update_slots: id 63 | task 26871 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2209. slot release: id 34 | task 26867 | stop processing: n_past = 131, truncated = 1
  2210. slot print_timing: id 34 | task 26867 |
  2211. prompt eval time = 323.07 ms / 199 tokens ( 1.62 ms per token, 615.96 tokens per second)
  2212. eval time = 9300.53 ms / 60 tokens ( 155.01 ms per token, 6.45 tokens per second)
  2213. total time = 9623.60 ms / 259 tokens
  2214. slot launch_slot_: id 34 | task 26899 | processing task
  2215. slot update_slots: id 28 | task 26872 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2216. slot update_slots: id 34 | task 26899 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2217. slot update_slots: id 34 | task 26899 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2218. slot update_slots: id 34 | task 26899 | kv cache rm [0, end)
  2219. slot update_slots: id 34 | task 26899 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2220. slot update_slots: id 34 | task 26899 | prompt done, n_past = 199, n_tokens = 262
  2221. slot release: id 28 | task 26872 | stop processing: n_past = 130, truncated = 1
  2222. slot print_timing: id 28 | task 26872 |
  2223. prompt eval time = 155.70 ms / 199 tokens ( 0.78 ms per token, 1278.07 tokens per second)
  2224. eval time = 9048.62 ms / 59 tokens ( 153.37 ms per token, 6.52 tokens per second)
  2225. total time = 9204.32 ms / 258 tokens
  2226. slot release: id 58 | task 27758 | stop processing: n_past = 172, truncated = 1
  2227. slot print_timing: id 58 | task 27758 |
  2228. prompt eval time = 449.96 ms / 199 tokens ( 2.26 ms per token, 442.26 tokens per second)
  2229. eval time = 16426.86 ms / 101 tokens ( 162.64 ms per token, 6.15 tokens per second)
  2230. total time = 16876.83 ms / 300 tokens
  2231. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2232. slot release: id 63 | task 26871 | stop processing: n_past = 131, truncated = 1
  2233. slot print_timing: id 63 | task 26871 |
  2234. prompt eval time = 331.37 ms / 199 tokens ( 1.67 ms per token, 600.53 tokens per second)
  2235. eval time = 9208.61 ms / 60 tokens ( 153.48 ms per token, 6.52 tokens per second)
  2236. total time = 9539.98 ms / 259 tokens
  2237. slot launch_slot_: id 28 | task 26900 | processing task
  2238. slot launch_slot_: id 58 | task 26901 | processing task
  2239. slot launch_slot_: id 63 | task 26902 | processing task
  2240. slot update_slots: id 28 | task 26900 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2241. slot update_slots: id 28 | task 26900 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2242. slot update_slots: id 28 | task 26900 | kv cache rm [0, end)
  2243. slot update_slots: id 28 | task 26900 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  2244. slot update_slots: id 28 | task 26900 | prompt done, n_past = 199, n_tokens = 260
  2245. slot update_slots: id 58 | task 26901 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2246. slot update_slots: id 58 | task 26901 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2247. slot update_slots: id 58 | task 26901 | kv cache rm [0, end)
  2248. slot update_slots: id 58 | task 26901 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  2249. slot update_slots: id 58 | task 26901 | prompt done, n_past = 199, n_tokens = 459
  2250. slot update_slots: id 63 | task 26902 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2251. slot update_slots: id 63 | task 26902 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2252. slot update_slots: id 63 | task 26902 | kv cache rm [0, end)
  2253. slot update_slots: id 63 | task 26902 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  2254. slot update_slots: id 63 | task 26902 | prompt done, n_past = 199, n_tokens = 658
  2255. srv params_from_: Chat format: Content-only
  2256. slot update_slots: id 56 | task 26873 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2257. slot release: id 56 | task 26873 | stop processing: n_past = 130, truncated = 1
  2258. slot print_timing: id 56 | task 26873 |
  2259. prompt eval time = 157.81 ms / 199 tokens ( 0.79 ms per token, 1260.99 tokens per second)
  2260. eval time = 9319.93 ms / 59 tokens ( 157.96 ms per token, 6.33 tokens per second)
  2261. total time = 9477.75 ms / 258 tokens
  2262. slot launch_slot_: id 56 | task 26907 | processing task
  2263. slot update_slots: id 24 | task 26621 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2264. slot update_slots: id 56 | task 26907 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2265. slot update_slots: id 56 | task 26907 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2266. slot update_slots: id 56 | task 26907 | kv cache rm [0, end)
  2267. slot update_slots: id 56 | task 26907 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2268. slot update_slots: id 56 | task 26907 | prompt done, n_past = 199, n_tokens = 262
  2269. srv cancel_tasks: cancel task, id_task = 27710
  2270. srv cancel_tasks: cancel task, id_task = 27626
  2271. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2272. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2273. srv cancel_tasks: cancel task, id_task = 27704
  2274. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2275. srv cancel_tasks: cancel task, id_task = 27708
  2276. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2277. srv cancel_tasks: cancel task, id_task = 27643
  2278. srv cancel_tasks: cancel task, id_task = 27623
  2279. srv cancel_tasks: cancel task, id_task = 27660
  2280. srv cancel_tasks: cancel task, id_task = 27675
  2281. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2282. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2283. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2284. srv cancel_tasks: cancel task, id_task = 27687
  2285. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2286. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2287. srv params_from_: Chat format: Content-only
  2288. srv params_from_: Chat format: Content-only
  2289. srv cancel_tasks: cancel task, id_task = 27646
  2290. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2291. srv cancel_tasks: cancel task, id_task = 27711
  2292. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2293. srv params_from_: Chat format: Content-only
  2294. srv cancel_tasks: cancel task, id_task = 27702
  2295. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2296. srv cancel_tasks: cancel task, id_task = 27621
  2297. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2298. srv cancel_tasks: cancel task, id_task = 27691
  2299. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2300. srv cancel_tasks: cancel task, id_task = 27624
  2301. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2302. srv params_from_: Chat format: Content-only
  2303. srv params_from_: Chat format: Content-only
  2304. srv params_from_: Chat format: Content-only
  2305. srv params_from_: Chat format: Content-only
  2306. srv params_from_: Chat format: Content-only
  2307. srv params_from_: Chat format: Content-only
  2308. srv cancel_tasks: cancel task, id_task = 27658
  2309. srv cancel_tasks: cancel task, id_task = 27652
  2310. srv cancel_tasks: cancel task, id_task = 27695
  2311. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2312. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2313. srv cancel_tasks: cancel task, id_task = 27632
  2314. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2315. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2316. srv cancel_tasks: cancel task, id_task = 27620
  2317. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2318. srv cancel_tasks: cancel task, id_task = 27686
  2319. srv cancel_tasks: cancel task, id_task = 27697
  2320. srv cancel_tasks: cancel task, id_task = 27724
  2321. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2322. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2323. srv cancel_tasks: cancel task, id_task = 27653
  2324. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2325. srv cancel_tasks: cancel task, id_task = 27667
  2326. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2327. srv cancel_tasks: cancel task, id_task = 27705
  2328. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2329. srv cancel_tasks: cancel task, id_task = 27706
  2330. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2331. srv params_from_: Chat format: Content-only
  2332. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2333. srv params_from_: Chat format: Content-only
  2334. srv params_from_: Chat format: Content-only
  2335. srv params_from_: Chat format: Content-only
  2336. srv params_from_: Chat format: Content-only
  2337. srv params_from_: Chat format: Content-only
  2338. srv params_from_: Chat format: Content-only
  2339. srv params_from_: Chat format: Content-only
  2340. srv params_from_: Chat format: Content-only
  2341. srv cancel_tasks: cancel task, id_task = 27641
  2342. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2343. srv cancel_tasks: cancel task, id_task = 27713
  2344. srv cancel_tasks: cancel task, id_task = 27720
  2345. srv cancel_tasks: cancel task, id_task = 27699
  2346. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2347. srv cancel_tasks: cancel task, id_task = 27618
  2348. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2349. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2350. srv cancel_tasks: cancel task, id_task = 27680
  2351. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2352. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2353. srv params_from_: Chat format: Content-only
  2354. srv params_from_: Chat format: Content-only
  2355. srv params_from_: Chat format: Content-only
  2356. srv params_from_: Chat format: Content-only
  2357. srv params_from_: Chat format: Content-only
  2358. srv params_from_: Chat format: Content-only
  2359. srv params_from_: Chat format: Content-only
  2360. srv cancel_tasks: cancel task, id_task = 27664
  2361. srv cancel_tasks: cancel task, id_task = 27672
  2362. srv cancel_tasks: cancel task, id_task = 27665
  2363. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2364. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2365. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2366. srv cancel_tasks: cancel task, id_task = 27656
  2367. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2368. srv params_from_: Chat format: Content-only
  2369. srv cancel_tasks: cancel task, id_task = 27619
  2370. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2371. srv cancel_tasks: cancel task, id_task = 27690
  2372. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2373. srv cancel_tasks: cancel task, id_task = 27703
  2374. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2375. srv params_from_: Chat format: Content-only
  2376. srv params_from_: Chat format: Content-only
  2377. srv params_from_: Chat format: Content-only
  2378. srv cancel_tasks: cancel task, id_task = 27709
  2379. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2380. srv params_from_: Chat format: Content-only
  2381. srv cancel_tasks: cancel task, id_task = 27716
  2382. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2383. srv params_from_: Chat format: Content-only
  2384. srv params_from_: Chat format: Content-only
  2385. srv params_from_: Chat format: Content-only
  2386. srv params_from_: Chat format: Content-only
  2387. srv cancel_tasks: cancel task, id_task = 27654
  2388. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2389. srv params_from_: Chat format: Content-only
  2390. srv params_from_: Chat format: Content-only
  2391. srv params_from_: Chat format: Content-only
  2392. srv params_from_: Chat format: Content-only
  2393. srv params_from_: Chat format: Content-only
  2394. srv params_from_: Chat format: Content-only
  2395. srv params_from_: Chat format: Content-only
  2396. srv params_from_: Chat format: Content-only
  2397. srv cancel_tasks: cancel task, id_task = 27670
  2398. srv cancel_tasks: cancel task, id_task = 27669
  2399. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2400. srv cancel_tasks: cancel task, id_task = 27688
  2401. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2402. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2403. srv cancel_tasks: cancel task, id_task = 27678
  2404. srv cancel_tasks: cancel task, id_task = 27657
  2405. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2406. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2407. srv params_from_: Chat format: Content-only
  2408. srv params_from_: Chat format: Content-only
  2409. srv params_from_: Chat format: Content-only
  2410. srv params_from_: Chat format: Content-only
  2411. srv params_from_: Chat format: Content-only
  2412. srv params_from_: Chat format: Content-only
  2413. slot update_slots: id 8 | task 26875 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2414. slot update_slots: id 14 | task 26627 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2415. slot release: id 47 | task 26852 | stop processing: n_past = 172, truncated = 1
  2416. slot print_timing: id 47 | task 26852 |
  2417. prompt eval time = 575.19 ms / 199 tokens ( 2.89 ms per token, 345.97 tokens per second)
  2418. eval time = 15239.12 ms / 101 tokens ( 150.88 ms per token, 6.63 tokens per second)
  2419. total time = 15814.31 ms / 300 tokens
  2420. slot launch_slot_: id 47 | task 26903 | processing task
  2421. slot update_slots: id 47 | task 26903 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2422. slot update_slots: id 47 | task 26903 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2423. slot update_slots: id 47 | task 26903 | kv cache rm [0, end)
  2424. slot update_slots: id 47 | task 26903 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2425. slot update_slots: id 47 | task 26903 | prompt done, n_past = 199, n_tokens = 262
  2426. slot release: id 8 | task 26875 | stop processing: n_past = 131, truncated = 1
  2427. slot print_timing: id 8 | task 26875 |
  2428. prompt eval time = 161.12 ms / 199 tokens ( 0.81 ms per token, 1235.10 tokens per second)
  2429. eval time = 9703.33 ms / 60 tokens ( 161.72 ms per token, 6.18 tokens per second)
  2430. total time = 9864.46 ms / 259 tokens
  2431. slot launch_slot_: id 8 | task 26904 | processing task
  2432. slot update_slots: id 41 | task 26876 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2433. slot update_slots: id 8 | task 26904 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2434. slot update_slots: id 8 | task 26904 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2435. slot update_slots: id 8 | task 26904 | kv cache rm [0, end)
  2436. slot update_slots: id 8 | task 26904 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2437. slot update_slots: id 8 | task 26904 | prompt done, n_past = 199, n_tokens = 262
  2438. srv cancel_tasks: cancel task, id_task = 27712
  2439. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2440. srv cancel_tasks: cancel task, id_task = 27707
  2441. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2442. slot release: id 41 | task 26876 | stop processing: n_past = 131, truncated = 1
  2443. slot print_timing: id 41 | task 26876 |
  2444. prompt eval time = 165.28 ms / 199 tokens ( 0.83 ms per token, 1204.00 tokens per second)
  2445. eval time = 9960.92 ms / 60 tokens ( 166.02 ms per token, 6.02 tokens per second)
  2446. total time = 10126.20 ms / 259 tokens
  2447. slot launch_slot_: id 41 | task 26912 | processing task
  2448. slot update_slots: id 13 | task 26877 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2449. slot update_slots: id 41 | task 26912 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2450. slot update_slots: id 41 | task 26912 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2451. slot update_slots: id 41 | task 26912 | kv cache rm [0, end)
  2452. slot update_slots: id 41 | task 26912 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2453. slot update_slots: id 41 | task 26912 | prompt done, n_past = 199, n_tokens = 262
  2454. slot update_slots: id 17 | task 26878 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2455. slot update_slots: id 45 | task 26879 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2456. slot update_slots: id 5 | task 26880 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2457. slot update_slots: id 40 | task 26882 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2458. slot update_slots: id 1 | task 26884 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2459. slot update_slots: id 18 | task 26885 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2460. slot release: id 45 | task 26879 | stop processing: n_past = 131, truncated = 1
  2461. slot print_timing: id 45 | task 26879 |
  2462. prompt eval time = 411.32 ms / 199 tokens ( 2.07 ms per token, 483.80 tokens per second)
  2463. eval time = 9663.02 ms / 60 tokens ( 161.05 ms per token, 6.21 tokens per second)
  2464. total time = 10074.34 ms / 259 tokens
  2465. slot launch_slot_: id 45 | task 26908 | processing task
  2466. slot update_slots: id 21 | task 26886 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2467. slot update_slots: id 45 | task 26908 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2468. slot update_slots: id 45 | task 26908 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2469. slot update_slots: id 45 | task 26908 | kv cache rm [0, end)
  2470. slot update_slots: id 45 | task 26908 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2471. slot update_slots: id 45 | task 26908 | prompt done, n_past = 199, n_tokens = 262
  2472. srv cancel_tasks: cancel task, id_task = 27714
  2473. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2474. slot release: id 5 | task 26880 | stop processing: n_past = 131, truncated = 1
  2475. slot print_timing: id 5 | task 26880 |
  2476. prompt eval time = 536.85 ms / 199 tokens ( 2.70 ms per token, 370.68 tokens per second)
  2477. eval time = 9499.17 ms / 60 tokens ( 158.32 ms per token, 6.32 tokens per second)
  2478. total time = 10036.02 ms / 259 tokens
  2479. slot release: id 40 | task 26882 | stop processing: n_past = 131, truncated = 1
  2480. slot print_timing: id 40 | task 26882 |
  2481. prompt eval time = 539.68 ms / 199 tokens ( 2.71 ms per token, 368.74 tokens per second)
  2482. eval time = 9499.06 ms / 60 tokens ( 158.32 ms per token, 6.32 tokens per second)
  2483. total time = 10038.74 ms / 259 tokens
  2484. slot launch_slot_: id 5 | task 26905 | processing task
  2485. slot launch_slot_: id 40 | task 26909 | processing task
  2486. slot update_slots: id 52 | task 26742 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2487. slot update_slots: id 5 | task 26905 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2488. slot update_slots: id 5 | task 26905 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2489. slot update_slots: id 5 | task 26905 | kv cache rm [0, end)
  2490. slot update_slots: id 5 | task 26905 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2491. slot update_slots: id 5 | task 26905 | prompt done, n_past = 199, n_tokens = 261
  2492. slot update_slots: id 40 | task 26909 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2493. slot update_slots: id 40 | task 26909 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2494. slot update_slots: id 40 | task 26909 | kv cache rm [0, end)
  2495. slot update_slots: id 40 | task 26909 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2496. slot update_slots: id 40 | task 26909 | prompt done, n_past = 199, n_tokens = 460
  2497. slot release: id 1 | task 26884 | stop processing: n_past = 131, truncated = 1
  2498. slot print_timing: id 1 | task 26884 |
  2499. prompt eval time = 457.78 ms / 199 tokens ( 2.30 ms per token, 434.70 tokens per second)
  2500. eval time = 9279.09 ms / 60 tokens ( 154.65 ms per token, 6.47 tokens per second)
  2501. total time = 9736.87 ms / 259 tokens
  2502. slot launch_slot_: id 1 | task 26911 | processing task
  2503. slot update_slots: id 42 | task 26888 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2504. slot update_slots: id 60 | task 26889 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2505. slot update_slots: id 1 | task 26911 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2506. slot update_slots: id 1 | task 26911 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2507. slot update_slots: id 1 | task 26911 | kv cache rm [0, end)
  2508. slot update_slots: id 1 | task 26911 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2509. slot update_slots: id 1 | task 26911 | prompt done, n_past = 199, n_tokens = 262
  2510. slot update_slots: id 51 | task 26891 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2511. slot update_slots: id 57 | task 26752 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2512. slot release: id 51 | task 26891 | stop processing: n_past = 131, truncated = 1
  2513. slot print_timing: id 51 | task 26891 |
  2514. prompt eval time = 330.27 ms / 199 tokens ( 1.66 ms per token, 602.54 tokens per second)
  2515. eval time = 8971.92 ms / 60 tokens ( 149.53 ms per token, 6.69 tokens per second)
  2516. total time = 9302.18 ms / 259 tokens
  2517. slot launch_slot_: id 51 | task 26910 | processing task
  2518. slot update_slots: id 51 | task 26910 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2519. slot update_slots: id 51 | task 26910 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2520. slot update_slots: id 51 | task 26910 | kv cache rm [0, end)
  2521. slot update_slots: id 51 | task 26910 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2522. slot update_slots: id 51 | task 26910 | prompt done, n_past = 199, n_tokens = 262
  2523. slot update_slots: id 26 | task 26892 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2524. slot update_slots: id 30 | task 26629 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2525. slot update_slots: id 6 | task 26605 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2526. srv cancel_tasks: cancel task, id_task = 27722
  2527. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2528. srv cancel_tasks: cancel task, id_task = 27715
  2529. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2530. slot release: id 26 | task 26892 | stop processing: n_past = 131, truncated = 1
  2531. slot print_timing: id 26 | task 26892 |
  2532. prompt eval time = 157.09 ms / 199 tokens ( 0.79 ms per token, 1266.80 tokens per second)
  2533. eval time = 8812.87 ms / 60 tokens ( 146.88 ms per token, 6.81 tokens per second)
  2534. total time = 8969.96 ms / 259 tokens
  2535. slot launch_slot_: id 26 | task 26906 | processing task
  2536. slot update_slots: id 3 | task 26893 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2537. slot update_slots: id 26 | task 26906 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2538. slot update_slots: id 26 | task 26906 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2539. slot update_slots: id 26 | task 26906 | kv cache rm [0, end)
  2540. slot update_slots: id 26 | task 26906 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2541. slot update_slots: id 26 | task 26906 | prompt done, n_past = 199, n_tokens = 262
  2542. slot update_slots: id 43 | task 26653 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2543. slot release: id 3 | task 26893 | stop processing: n_past = 131, truncated = 1
  2544. slot print_timing: id 3 | task 26893 |
  2545. prompt eval time = 149.76 ms / 199 tokens ( 0.75 ms per token, 1328.78 tokens per second)
  2546. eval time = 8974.61 ms / 60 tokens ( 149.58 ms per token, 6.69 tokens per second)
  2547. total time = 9124.38 ms / 259 tokens
  2548. slot launch_slot_: id 3 | task 26913 | processing task
  2549. slot update_slots: id 3 | task 26913 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2550. slot update_slots: id 3 | task 26913 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2551. slot update_slots: id 3 | task 26913 | kv cache rm [0, end)
  2552. slot update_slots: id 3 | task 26913 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2553. slot update_slots: id 3 | task 26913 | prompt done, n_past = 199, n_tokens = 262
  2554. slot release: id 20 | task 26848 | stop processing: n_past = 195, truncated = 1
  2555. slot print_timing: id 20 | task 26848 |
  2556. prompt eval time = 573.20 ms / 199 tokens ( 2.88 ms per token, 347.17 tokens per second)
  2557. eval time = 19664.58 ms / 124 tokens ( 158.59 ms per token, 6.31 tokens per second)
  2558. total time = 20237.78 ms / 323 tokens
  2559. slot launch_slot_: id 20 | task 26914 | processing task
  2560. slot update_slots: id 20 | task 26914 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2561. slot update_slots: id 20 | task 26914 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2562. slot update_slots: id 20 | task 26914 | kv cache rm [0, end)
  2563. slot update_slots: id 20 | task 26914 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2564. slot update_slots: id 20 | task 26914 | prompt done, n_past = 199, n_tokens = 262
  2565. srv cancel_tasks: cancel task, id_task = 27721
  2566. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2567. slot update_slots: id 19 | task 26483 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2568. slot update_slots: id 22 | task 26488 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2569. slot update_slots: id 23 | task 26535 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2570. slot update_slots: id 25 | task 26512 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2571. slot update_slots: id 35 | task 26522 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2572. slot update_slots: id 37 | task 26484 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2573. slot update_slots: id 48 | task 26498 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2574. slot update_slots: id 53 | task 26776 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2575. slot update_slots: id 54 | task 26525 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2576. slot release: id 39 | task 26861 | stop processing: n_past = 172, truncated = 1
  2577. slot print_timing: id 39 | task 26861 |
  2578. prompt eval time = 233.93 ms / 199 tokens ( 1.18 ms per token, 850.69 tokens per second)
  2579. eval time = 17145.24 ms / 101 tokens ( 169.75 ms per token, 5.89 tokens per second)
  2580. total time = 17379.17 ms / 300 tokens
  2581. slot launch_slot_: id 39 | task 26915 | processing task
  2582. slot update_slots: id 59 | task 26894 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2583. slot update_slots: id 39 | task 26915 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2584. slot update_slots: id 39 | task 26915 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2585. slot update_slots: id 39 | task 26915 | kv cache rm [0, end)
  2586. slot update_slots: id 39 | task 26915 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2587. slot update_slots: id 39 | task 26915 | prompt done, n_past = 199, n_tokens = 262
  2588. slot release: id 2 | task 26864 | stop processing: n_past = 172, truncated = 1
  2589. slot print_timing: id 2 | task 26864 |
  2590. prompt eval time = 154.00 ms / 199 tokens ( 0.77 ms per token, 1292.22 tokens per second)
  2591. eval time = 17307.59 ms / 101 tokens ( 171.36 ms per token, 5.84 tokens per second)
  2592. total time = 17461.59 ms / 300 tokens
  2593. slot launch_slot_: id 2 | task 26916 | processing task
  2594. slot update_slots: id 2 | task 26916 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2595. slot update_slots: id 2 | task 26916 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2596. slot update_slots: id 2 | task 26916 | kv cache rm [0, end)
  2597. slot update_slots: id 2 | task 26916 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2598. slot update_slots: id 2 | task 26916 | prompt done, n_past = 199, n_tokens = 262
  2599. srv cancel_tasks: cancel task, id_task = 27719
  2600. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2601. srv cancel_tasks: cancel task, id_task = 27725
  2602. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2603. srv cancel_tasks: cancel task, id_task = 27717
  2604. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2605. srv cancel_tasks: cancel task, id_task = 27723
  2606. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2607. slot release: id 59 | task 26894 | stop processing: n_past = 130, truncated = 1
  2608. slot print_timing: id 59 | task 26894 |
  2609. prompt eval time = 157.73 ms / 199 tokens ( 0.79 ms per token, 1261.65 tokens per second)
  2610. eval time = 9723.99 ms / 59 tokens ( 164.81 ms per token, 6.07 tokens per second)
  2611. total time = 9881.72 ms / 258 tokens
  2612. slot launch_slot_: id 59 | task 26917 | processing task
  2613. slot update_slots: id 59 | task 26917 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2614. slot update_slots: id 59 | task 26917 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2615. slot update_slots: id 59 | task 26917 | kv cache rm [0, end)
  2616. slot update_slots: id 59 | task 26917 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2617. slot update_slots: id 59 | task 26917 | prompt done, n_past = 199, n_tokens = 262
  2618. slot update_slots: id 46 | task 26895 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2619. slot release: id 31 | task 26868 | stop processing: n_past = 172, truncated = 1
  2620. slot print_timing: id 31 | task 26868 |
  2621. prompt eval time = 237.47 ms / 199 tokens ( 1.19 ms per token, 838.00 tokens per second)
  2622. eval time = 17039.19 ms / 101 tokens ( 168.70 ms per token, 5.93 tokens per second)
  2623. total time = 17276.66 ms / 300 tokens
  2624. slot launch_slot_: id 31 | task 26918 | processing task
  2625. slot update_slots: id 31 | task 26918 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2626. slot update_slots: id 31 | task 26918 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2627. slot update_slots: id 31 | task 26918 | kv cache rm [0, end)
  2628. slot update_slots: id 31 | task 26918 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2629. slot update_slots: id 31 | task 26918 | prompt done, n_past = 199, n_tokens = 262
  2630. slot update_slots: id 27 | task 26896 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2631. slot release: id 27 | task 26896 | stop processing: n_past = 131, truncated = 1
  2632. slot print_timing: id 27 | task 26896 |
  2633. prompt eval time = 156.44 ms / 199 tokens ( 0.79 ms per token, 1272.01 tokens per second)
  2634. eval time = 9754.54 ms / 60 tokens ( 162.58 ms per token, 6.15 tokens per second)
  2635. total time = 9910.99 ms / 259 tokens
  2636. slot launch_slot_: id 27 | task 26919 | processing task
  2637. slot update_slots: id 27 | task 26919 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2638. slot update_slots: id 27 | task 26919 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2639. slot update_slots: id 27 | task 26919 | kv cache rm [0, end)
  2640. slot update_slots: id 27 | task 26919 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2641. slot update_slots: id 27 | task 26919 | prompt done, n_past = 199, n_tokens = 262
  2642. srv cancel_tasks: cancel task, id_task = 27727
  2643. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2644. srv cancel_tasks: cancel task, id_task = 27718
  2645. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2646. srv cancel_tasks: cancel task, id_task = 27739
  2647. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2648. slot update_slots: id 12 | task 26897 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2649. slot update_slots: id 7 | task 26898 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2650. slot release: id 12 | task 26897 | stop processing: n_past = 131, truncated = 1
  2651. slot print_timing: id 12 | task 26897 |
  2652. prompt eval time = 323.11 ms / 199 tokens ( 1.62 ms per token, 615.90 tokens per second)
  2653. eval time = 9915.13 ms / 60 tokens ( 165.25 ms per token, 6.05 tokens per second)
  2654. total time = 10238.23 ms / 259 tokens
  2655. slot launch_slot_: id 12 | task 26920 | processing task
  2656. slot update_slots: id 12 | task 26920 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2657. slot update_slots: id 12 | task 26920 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2658. slot update_slots: id 12 | task 26920 | kv cache rm [0, end)
  2659. slot update_slots: id 12 | task 26920 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2660. slot update_slots: id 12 | task 26920 | prompt done, n_past = 199, n_tokens = 262
  2661. slot release: id 7 | task 26898 | stop processing: n_past = 131, truncated = 1
  2662. slot print_timing: id 7 | task 26898 |
  2663. prompt eval time = 316.96 ms / 199 tokens ( 1.59 ms per token, 627.84 tokens per second)
  2664. eval time = 9743.28 ms / 60 tokens ( 162.39 ms per token, 6.16 tokens per second)
  2665. total time = 10060.24 ms / 259 tokens
  2666. slot launch_slot_: id 7 | task 26921 | processing task
  2667. slot update_slots: id 34 | task 26899 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2668. slot update_slots: id 7 | task 26921 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2669. slot update_slots: id 7 | task 26921 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2670. slot update_slots: id 7 | task 26921 | kv cache rm [0, end)
  2671. slot update_slots: id 7 | task 26921 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2672. slot update_slots: id 7 | task 26921 | prompt done, n_past = 199, n_tokens = 262
  2673. slot update_slots: id 4 | task 26792 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2674. slot update_slots: id 15 | task 26795 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2675. slot update_slots: id 28 | task 26900 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2676. slot update_slots: id 58 | task 26901 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2677. slot update_slots: id 63 | task 26902 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2678. slot release: id 34 | task 26899 | stop processing: n_past = 131, truncated = 1
  2679. slot print_timing: id 34 | task 26899 |
  2680. prompt eval time = 159.89 ms / 199 tokens ( 0.80 ms per token, 1244.59 tokens per second)
  2681. eval time = 9921.87 ms / 60 tokens ( 165.36 ms per token, 6.05 tokens per second)
  2682. total time = 10081.76 ms / 259 tokens
  2683. slot launch_slot_: id 34 | task 26922 | processing task
  2684. slot update_slots: id 34 | task 26922 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2685. slot update_slots: id 34 | task 26922 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2686. slot update_slots: id 34 | task 26922 | kv cache rm [0, end)
  2687. slot update_slots: id 34 | task 26922 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2688. slot update_slots: id 34 | task 26922 | prompt done, n_past = 199, n_tokens = 262
  2689. slot release: id 58 | task 26901 | stop processing: n_past = 130, truncated = 1
  2690. slot print_timing: id 58 | task 26901 |
  2691. prompt eval time = 345.64 ms / 199 tokens ( 1.74 ms per token, 575.74 tokens per second)
  2692. eval time = 9684.24 ms / 59 tokens ( 164.14 ms per token, 6.09 tokens per second)
  2693. total time = 10029.88 ms / 258 tokens
  2694. slot release: id 63 | task 26902 | stop processing: n_past = 130, truncated = 1
  2695. slot print_timing: id 63 | task 26902 |
  2696. prompt eval time = 345.95 ms / 199 tokens ( 1.74 ms per token, 575.22 tokens per second)
  2697. eval time = 9684.26 ms / 59 tokens ( 164.14 ms per token, 6.09 tokens per second)
  2698. total time = 10030.22 ms / 258 tokens
  2699. slot launch_slot_: id 58 | task 26923 | processing task
  2700. slot launch_slot_: id 63 | task 26928 | processing task
  2701. slot update_slots: id 58 | task 26923 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2702. slot update_slots: id 58 | task 26923 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2703. slot update_slots: id 58 | task 26923 | kv cache rm [0, end)
  2704. slot update_slots: id 58 | task 26923 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2705. slot update_slots: id 58 | task 26923 | prompt done, n_past = 199, n_tokens = 261
  2706. slot update_slots: id 63 | task 26928 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2707. slot update_slots: id 63 | task 26928 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2708. slot update_slots: id 63 | task 26928 | kv cache rm [0, end)
  2709. slot update_slots: id 63 | task 26928 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2710. slot update_slots: id 63 | task 26928 | prompt done, n_past = 199, n_tokens = 460
  2711. srv cancel_tasks: cancel task, id_task = 27741
  2712. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2713. srv cancel_tasks: cancel task, id_task = 27744
  2714. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2715. srv cancel_tasks: cancel task, id_task = 27750
  2716. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2717. slot release: id 18 | task 26885 | stop processing: n_past = 172, truncated = 1
  2718. slot print_timing: id 18 | task 26885 |
  2719. prompt eval time = 459.02 ms / 199 tokens ( 2.31 ms per token, 433.53 tokens per second)
  2720. eval time = 16200.49 ms / 101 tokens ( 160.40 ms per token, 6.23 tokens per second)
  2721. total time = 16659.52 ms / 300 tokens
  2722. slot release: id 28 | task 26900 | stop processing: n_past = 131, truncated = 1
  2723. slot print_timing: id 28 | task 26900 |
  2724. prompt eval time = 343.23 ms / 199 tokens ( 1.72 ms per token, 579.79 tokens per second)
  2725. eval time = 10208.20 ms / 60 tokens ( 170.14 ms per token, 5.88 tokens per second)
  2726. total time = 10551.43 ms / 259 tokens
  2727. slot release: id 29 | task 26865 | stop processing: n_past = 194, truncated = 1
  2728. slot print_timing: id 29 | task 26865 |
  2729. prompt eval time = 402.41 ms / 199 tokens ( 2.02 ms per token, 494.52 tokens per second)
  2730. eval time = 20663.80 ms / 123 tokens ( 168.00 ms per token, 5.95 tokens per second)
  2731. total time = 21066.21 ms / 322 tokens
  2732. slot launch_slot_: id 18 | task 26929 | processing task
  2733. slot launch_slot_: id 28 | task 26930 | processing task
  2734. slot launch_slot_: id 29 | task 26931 | processing task
  2735. slot update_slots: id 56 | task 26907 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2736. slot update_slots: id 18 | task 26929 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2737. slot update_slots: id 18 | task 26929 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2738. slot update_slots: id 18 | task 26929 | kv cache rm [0, end)
  2739. slot update_slots: id 18 | task 26929 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  2740. slot update_slots: id 18 | task 26929 | prompt done, n_past = 199, n_tokens = 260
  2741. slot update_slots: id 28 | task 26930 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2742. slot update_slots: id 28 | task 26930 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2743. slot update_slots: id 28 | task 26930 | kv cache rm [0, end)
  2744. slot update_slots: id 28 | task 26930 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  2745. slot update_slots: id 28 | task 26930 | prompt done, n_past = 199, n_tokens = 459
  2746. slot update_slots: id 29 | task 26931 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2747. slot update_slots: id 29 | task 26931 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2748. slot update_slots: id 29 | task 26931 | kv cache rm [0, end)
  2749. slot update_slots: id 29 | task 26931 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  2750. slot update_slots: id 29 | task 26931 | prompt done, n_past = 199, n_tokens = 658
  2751. srv cancel_tasks: cancel task, id_task = 27819
  2752. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2753. srv cancel_tasks: cancel task, id_task = 27877
  2754. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2755. srv cancel_tasks: cancel task, id_task = 27862
  2756. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2757. slot update_slots: id 11 | task 26813 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2758. slot release: id 42 | task 26888 | stop processing: n_past = 172, truncated = 1
  2759. slot print_timing: id 42 | task 26888 |
  2760. prompt eval time = 238.41 ms / 199 tokens ( 1.20 ms per token, 834.70 tokens per second)
  2761. eval time = 16668.91 ms / 101 tokens ( 165.04 ms per token, 6.06 tokens per second)
  2762. total time = 16907.32 ms / 300 tokens
  2763. slot release: id 56 | task 26907 | stop processing: n_past = 131, truncated = 1
  2764. slot print_timing: id 56 | task 26907 |
  2765. prompt eval time = 163.09 ms / 199 tokens ( 0.82 ms per token, 1220.19 tokens per second)
  2766. eval time = 10980.62 ms / 60 tokens ( 183.01 ms per token, 5.46 tokens per second)
  2767. total time = 11143.71 ms / 259 tokens
  2768. slot release: id 60 | task 26889 | stop processing: n_past = 172, truncated = 1
  2769. slot print_timing: id 60 | task 26889 |
  2770. prompt eval time = 241.09 ms / 199 tokens ( 1.21 ms per token, 825.43 tokens per second)
  2771. eval time = 16667.74 ms / 101 tokens ( 165.03 ms per token, 6.06 tokens per second)
  2772. total time = 16908.82 ms / 300 tokens
  2773. slot launch_slot_: id 42 | task 26932 | processing task
  2774. slot launch_slot_: id 56 | task 26934 | processing task
  2775. slot launch_slot_: id 60 | task 26936 | processing task
  2776. slot update_slots: id 42 | task 26932 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2777. slot update_slots: id 42 | task 26932 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2778. slot update_slots: id 42 | task 26932 | kv cache rm [0, end)
  2779. slot update_slots: id 42 | task 26932 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  2780. slot update_slots: id 42 | task 26932 | prompt done, n_past = 199, n_tokens = 260
  2781. slot update_slots: id 56 | task 26934 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2782. slot update_slots: id 56 | task 26934 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2783. slot update_slots: id 56 | task 26934 | kv cache rm [0, end)
  2784. slot update_slots: id 56 | task 26934 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  2785. slot update_slots: id 56 | task 26934 | prompt done, n_past = 199, n_tokens = 459
  2786. slot update_slots: id 60 | task 26936 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2787. slot update_slots: id 60 | task 26936 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2788. slot update_slots: id 60 | task 26936 | kv cache rm [0, end)
  2789. slot update_slots: id 60 | task 26936 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  2790. slot update_slots: id 60 | task 26936 | prompt done, n_past = 199, n_tokens = 658
  2791. srv cancel_tasks: cancel task, id_task = 27886
  2792. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2793. srv cancel_tasks: cancel task, id_task = 27876
  2794. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2795. slot update_slots: id 47 | task 26903 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2796. slot update_slots: id 55 | task 26686 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2797. slot update_slots: id 8 | task 26904 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2798. slot update_slots: id 41 | task 26912 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2799. srv cancel_tasks: cancel task, id_task = 27890
  2800. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2801. srv cancel_tasks: cancel task, id_task = 27880
  2802. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2803. slot release: id 41 | task 26912 | stop processing: n_past = 131, truncated = 1
  2804. slot print_timing: id 41 | task 26912 |
  2805. prompt eval time = 163.48 ms / 199 tokens ( 0.82 ms per token, 1217.30 tokens per second)
  2806. eval time = 10786.70 ms / 60 tokens ( 179.78 ms per token, 5.56 tokens per second)
  2807. total time = 10950.18 ms / 259 tokens
  2808. slot launch_slot_: id 41 | task 26937 | processing task
  2809. slot update_slots: id 10 | task 26821 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2810. slot update_slots: id 41 | task 26937 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2811. slot update_slots: id 41 | task 26937 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2812. slot update_slots: id 41 | task 26937 | kv cache rm [0, end)
  2813. slot update_slots: id 41 | task 26937 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2814. slot update_slots: id 41 | task 26937 | prompt done, n_past = 199, n_tokens = 262
  2815. slot update_slots: id 45 | task 26908 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2816. slot update_slots: id 5 | task 26905 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2817. slot update_slots: id 40 | task 26909 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2818. slot update_slots: id 1 | task 26911 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2819. srv cancel_tasks: cancel task, id_task = 27885
  2820. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2821. slot release: id 40 | task 26909 | stop processing: n_past = 131, truncated = 1
  2822. slot print_timing: id 40 | task 26909 |
  2823. prompt eval time = 242.37 ms / 199 tokens ( 1.22 ms per token, 821.06 tokens per second)
  2824. eval time = 10481.69 ms / 60 tokens ( 174.69 ms per token, 5.72 tokens per second)
  2825. total time = 10724.06 ms / 259 tokens
  2826. slot launch_slot_: id 40 | task 26949 | processing task
  2827. slot update_slots: id 9 | task 26823 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2828. slot update_slots: id 40 | task 26949 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2829. slot update_slots: id 40 | task 26949 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2830. slot update_slots: id 40 | task 26949 | kv cache rm [0, end)
  2831. slot update_slots: id 40 | task 26949 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2832. slot update_slots: id 40 | task 26949 | prompt done, n_past = 199, n_tokens = 262
  2833. slot update_slots: id 51 | task 26910 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2834. slot release: id 51 | task 26910 | stop processing: n_past = 131, truncated = 1
  2835. slot print_timing: id 51 | task 26910 |
  2836. prompt eval time = 156.56 ms / 199 tokens ( 0.79 ms per token, 1271.07 tokens per second)
  2837. eval time = 10008.46 ms / 60 tokens ( 166.81 ms per token, 5.99 tokens per second)
  2838. total time = 10165.02 ms / 259 tokens
  2839. slot launch_slot_: id 51 | task 26948 | processing task
  2840. slot update_slots: id 51 | task 26948 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2841. slot update_slots: id 51 | task 26948 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2842. slot update_slots: id 51 | task 26948 | kv cache rm [0, end)
  2843. slot update_slots: id 51 | task 26948 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2844. slot update_slots: id 51 | task 26948 | prompt done, n_past = 199, n_tokens = 262
  2845. slot release: id 21 | task 26886 | stop processing: n_past = 195, truncated = 1
  2846. slot print_timing: id 21 | task 26886 |
  2847. prompt eval time = 355.54 ms / 199 tokens ( 1.79 ms per token, 559.72 tokens per second)
  2848. eval time = 20099.73 ms / 124 tokens ( 162.09 ms per token, 6.17 tokens per second)
  2849. total time = 20455.27 ms / 323 tokens
  2850. slot launch_slot_: id 21 | task 26951 | processing task
  2851. slot update_slots: id 21 | task 26951 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2852. slot update_slots: id 21 | task 26951 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2853. slot update_slots: id 21 | task 26951 | kv cache rm [0, end)
  2854. slot update_slots: id 21 | task 26951 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2855. slot update_slots: id 21 | task 26951 | prompt done, n_past = 199, n_tokens = 262
  2856. slot update_slots: id 26 | task 26906 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2857. srv cancel_tasks: cancel task, id_task = 27902
  2858. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2859. srv cancel_tasks: cancel task, id_task = 27889
  2860. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2861. srv cancel_tasks: cancel task, id_task = 27888
  2862. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2863. srv cancel_tasks: cancel task, id_task = 27887
  2864. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2865. slot update_slots: id 0 | task 26700 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2866. slot release: id 26 | task 26906 | stop processing: n_past = 131, truncated = 1
  2867. slot print_timing: id 26 | task 26906 |
  2868. prompt eval time = 321.53 ms / 199 tokens ( 1.62 ms per token, 618.92 tokens per second)
  2869. eval time = 9942.70 ms / 60 tokens ( 165.71 ms per token, 6.03 tokens per second)
  2870. total time = 10264.23 ms / 259 tokens
  2871. slot launch_slot_: id 26 | task 26954 | processing task
  2872. slot update_slots: id 3 | task 26913 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2873. slot update_slots: id 26 | task 26954 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2874. slot update_slots: id 26 | task 26954 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2875. slot update_slots: id 26 | task 26954 | kv cache rm [0, end)
  2876. slot update_slots: id 26 | task 26954 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2877. slot update_slots: id 26 | task 26954 | prompt done, n_past = 199, n_tokens = 262
  2878. slot release: id 17 | task 26878 | stop processing: n_past = 203, truncated = 1
  2879. slot print_timing: id 17 | task 26878 |
  2880. prompt eval time = 409.12 ms / 199 tokens ( 2.06 ms per token, 486.41 tokens per second)
  2881. eval time = 22132.62 ms / 132 tokens ( 167.67 ms per token, 5.96 tokens per second)
  2882. total time = 22541.73 ms / 331 tokens
  2883. slot launch_slot_: id 17 | task 26956 | processing task
  2884. slot update_slots: id 20 | task 26914 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2885. slot update_slots: id 17 | task 26956 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2886. slot update_slots: id 17 | task 26956 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2887. slot update_slots: id 17 | task 26956 | kv cache rm [0, end)
  2888. slot update_slots: id 17 | task 26956 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2889. slot update_slots: id 17 | task 26956 | prompt done, n_past = 199, n_tokens = 262
  2890. slot update_slots: id 49 | task 26713 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2891. slot update_slots: id 61 | task 26715 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2892. slot release: id 3 | task 26913 | stop processing: n_past = 131, truncated = 1
  2893. slot print_timing: id 3 | task 26913 |
  2894. prompt eval time = 152.36 ms / 199 tokens ( 0.77 ms per token, 1306.12 tokens per second)
  2895. eval time = 10432.18 ms / 60 tokens ( 173.87 ms per token, 5.75 tokens per second)
  2896. total time = 10584.54 ms / 259 tokens
  2897. slot release: id 20 | task 26914 | stop processing: n_past = 130, truncated = 1
  2898. slot print_timing: id 20 | task 26914 |
  2899. prompt eval time = 155.53 ms / 199 tokens ( 0.78 ms per token, 1279.46 tokens per second)
  2900. eval time = 10273.32 ms / 59 tokens ( 174.12 ms per token, 5.74 tokens per second)
  2901. total time = 10428.85 ms / 258 tokens
  2902. slot launch_slot_: id 3 | task 26961 | processing task
  2903. slot launch_slot_: id 20 | task 26965 | processing task
  2904. slot update_slots: id 32 | task 26846 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2905. slot update_slots: id 3 | task 26961 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2906. slot update_slots: id 3 | task 26961 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2907. slot update_slots: id 3 | task 26961 | kv cache rm [0, end)
  2908. slot update_slots: id 3 | task 26961 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  2909. slot update_slots: id 3 | task 26961 | prompt done, n_past = 199, n_tokens = 261
  2910. slot update_slots: id 20 | task 26965 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2911. slot update_slots: id 20 | task 26965 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2912. slot update_slots: id 20 | task 26965 | kv cache rm [0, end)
  2913. slot update_slots: id 20 | task 26965 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  2914. slot update_slots: id 20 | task 26965 | prompt done, n_past = 199, n_tokens = 460
  2915. srv cancel_tasks: cancel task, id_task = 27904
  2916. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2917. srv cancel_tasks: cancel task, id_task = 27905
  2918. srv cancel_tasks: cancel task, id_task = 27906
  2919. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2920. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2921. slot update_slots: id 39 | task 26915 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2922. slot update_slots: id 2 | task 26916 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2923. slot update_slots: id 16 | task 26582 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2924. slot update_slots: id 59 | task 26917 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2925. slot release: id 39 | task 26915 | stop processing: n_past = 131, truncated = 1
  2926. slot print_timing: id 39 | task 26915 |
  2927. prompt eval time = 320.24 ms / 199 tokens ( 1.61 ms per token, 621.42 tokens per second)
  2928. eval time = 10784.78 ms / 60 tokens ( 179.75 ms per token, 5.56 tokens per second)
  2929. total time = 11105.02 ms / 259 tokens
  2930. slot launch_slot_: id 39 | task 26966 | processing task
  2931. slot update_slots: id 38 | task 26598 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2932. slot update_slots: id 44 | task 26608 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2933. slot update_slots: id 39 | task 26966 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2934. slot update_slots: id 39 | task 26966 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2935. slot update_slots: id 39 | task 26966 | kv cache rm [0, end)
  2936. slot update_slots: id 39 | task 26966 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2937. slot update_slots: id 39 | task 26966 | prompt done, n_past = 199, n_tokens = 262
  2938. slot release: id 2 | task 26916 | stop processing: n_past = 131, truncated = 1
  2939. slot print_timing: id 2 | task 26916 |
  2940. prompt eval time = 321.62 ms / 199 tokens ( 1.62 ms per token, 618.74 tokens per second)
  2941. eval time = 10863.38 ms / 60 tokens ( 181.06 ms per token, 5.52 tokens per second)
  2942. total time = 11185.01 ms / 259 tokens
  2943. slot launch_slot_: id 2 | task 26967 | processing task
  2944. slot update_slots: id 31 | task 26918 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2945. slot update_slots: id 62 | task 26614 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2946. slot update_slots: id 2 | task 26967 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2947. slot update_slots: id 2 | task 26967 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2948. slot update_slots: id 2 | task 26967 | kv cache rm [0, end)
  2949. slot update_slots: id 2 | task 26967 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2950. slot update_slots: id 2 | task 26967 | prompt done, n_past = 199, n_tokens = 262
  2951. srv cancel_tasks: cancel task, id_task = 27907
  2952. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2953. srv cancel_tasks: cancel task, id_task = 27910
  2954. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2955. slot release: id 59 | task 26917 | stop processing: n_past = 131, truncated = 1
  2956. slot print_timing: id 59 | task 26917 |
  2957. prompt eval time = 321.68 ms / 199 tokens ( 1.62 ms per token, 618.63 tokens per second)
  2958. eval time = 10949.05 ms / 60 tokens ( 182.48 ms per token, 5.48 tokens per second)
  2959. total time = 11270.73 ms / 259 tokens
  2960. slot launch_slot_: id 59 | task 26968 | processing task
  2961. slot update_slots: id 59 | task 26968 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2962. slot update_slots: id 59 | task 26968 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2963. slot update_slots: id 59 | task 26968 | kv cache rm [0, end)
  2964. slot update_slots: id 59 | task 26968 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2965. slot update_slots: id 59 | task 26968 | prompt done, n_past = 199, n_tokens = 262
  2966. slot release: id 31 | task 26918 | stop processing: n_past = 131, truncated = 1
  2967. slot print_timing: id 31 | task 26918 |
  2968. prompt eval time = 149.69 ms / 199 tokens ( 0.75 ms per token, 1329.39 tokens per second)
  2969. eval time = 11218.19 ms / 60 tokens ( 186.97 ms per token, 5.35 tokens per second)
  2970. total time = 11367.88 ms / 259 tokens
  2971. slot launch_slot_: id 31 | task 26969 | processing task
  2972. slot update_slots: id 31 | task 26969 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2973. slot update_slots: id 31 | task 26969 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2974. slot update_slots: id 31 | task 26969 | kv cache rm [0, end)
  2975. slot update_slots: id 31 | task 26969 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2976. slot update_slots: id 31 | task 26969 | prompt done, n_past = 199, n_tokens = 262
  2977. srv cancel_tasks: cancel task, id_task = 27909
  2978. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2979. srv cancel_tasks: cancel task, id_task = 27921
  2980. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2981. srv cancel_tasks: cancel task, id_task = 27911
  2982. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2983. srv cancel_tasks: cancel task, id_task = 27908
  2984. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  2985. slot update_slots: id 27 | task 26919 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2986. slot update_slots: id 33 | task 26851 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2987. slot update_slots: id 12 | task 26920 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2988. slot update_slots: id 7 | task 26921 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  2989. slot release: id 12 | task 26920 | stop processing: n_past = 131, truncated = 1
  2990. slot print_timing: id 12 | task 26920 |
  2991. prompt eval time = 152.80 ms / 199 tokens ( 0.77 ms per token, 1302.37 tokens per second)
  2992. eval time = 10763.58 ms / 60 tokens ( 179.39 ms per token, 5.57 tokens per second)
  2993. total time = 10916.38 ms / 259 tokens
  2994. slot launch_slot_: id 12 | task 26970 | processing task
  2995. slot update_slots: id 12 | task 26970 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  2996. slot update_slots: id 12 | task 26970 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  2997. slot update_slots: id 12 | task 26970 | kv cache rm [0, end)
  2998. slot update_slots: id 12 | task 26970 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  2999. slot update_slots: id 12 | task 26970 | prompt done, n_past = 199, n_tokens = 262
  3000. slot release: id 7 | task 26921 | stop processing: n_past = 131, truncated = 1
  3001. slot print_timing: id 7 | task 26921 |
  3002. prompt eval time = 157.96 ms / 199 tokens ( 0.79 ms per token, 1259.82 tokens per second)
  3003. eval time = 10758.80 ms / 60 tokens ( 179.31 ms per token, 5.58 tokens per second)
  3004. total time = 10916.76 ms / 259 tokens
  3005. slot launch_slot_: id 7 | task 26972 | processing task
  3006. slot update_slots: id 34 | task 26922 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3007. slot update_slots: id 7 | task 26972 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3008. slot update_slots: id 7 | task 26972 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3009. slot update_slots: id 7 | task 26972 | kv cache rm [0, end)
  3010. slot update_slots: id 7 | task 26972 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3011. slot update_slots: id 7 | task 26972 | prompt done, n_past = 199, n_tokens = 262
  3012. slot update_slots: id 58 | task 26923 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3013. slot update_slots: id 63 | task 26928 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3014. slot update_slots: id 18 | task 26929 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3015. slot update_slots: id 28 | task 26930 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3016. slot update_slots: id 29 | task 26931 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3017. slot release: id 63 | task 26928 | stop processing: n_past = 131, truncated = 1
  3018. slot print_timing: id 63 | task 26928 |
  3019. prompt eval time = 523.78 ms / 199 tokens ( 2.63 ms per token, 379.93 tokens per second)
  3020. eval time = 10368.32 ms / 60 tokens ( 172.81 ms per token, 5.79 tokens per second)
  3021. total time = 10892.09 ms / 259 tokens
  3022. slot launch_slot_: id 63 | task 26973 | processing task
  3023. slot update_slots: id 63 | task 26973 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3024. slot update_slots: id 63 | task 26973 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3025. slot update_slots: id 63 | task 26973 | kv cache rm [0, end)
  3026. slot update_slots: id 63 | task 26973 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3027. slot update_slots: id 63 | task 26973 | prompt done, n_past = 199, n_tokens = 262
  3028. srv cancel_tasks: cancel task, id_task = 27924
  3029. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3030. slot release: id 1 | task 26911 | stop processing: n_past = 172, truncated = 1
  3031. slot print_timing: id 1 | task 26911 |
  3032. prompt eval time = 346.93 ms / 199 tokens ( 1.74 ms per token, 573.60 tokens per second)
  3033. eval time = 17093.13 ms / 101 tokens ( 169.24 ms per token, 5.91 tokens per second)
  3034. total time = 17440.06 ms / 300 tokens
  3035. slot release: id 18 | task 26929 | stop processing: n_past = 131, truncated = 1
  3036. slot print_timing: id 18 | task 26929 |
  3037. prompt eval time = 653.87 ms / 199 tokens ( 3.29 ms per token, 304.34 tokens per second)
  3038. eval time = 9866.25 ms / 60 tokens ( 164.44 ms per token, 6.08 tokens per second)
  3039. total time = 10520.12 ms / 259 tokens
  3040. slot release: id 28 | task 26930 | stop processing: n_past = 131, truncated = 1
  3041. slot print_timing: id 28 | task 26930 |
  3042. prompt eval time = 654.73 ms / 199 tokens ( 3.29 ms per token, 303.94 tokens per second)
  3043. eval time = 9866.12 ms / 60 tokens ( 164.44 ms per token, 6.08 tokens per second)
  3044. total time = 10520.86 ms / 259 tokens
  3045. slot release: id 29 | task 26931 | stop processing: n_past = 131, truncated = 1
  3046. slot print_timing: id 29 | task 26931 |
  3047. prompt eval time = 654.76 ms / 199 tokens ( 3.29 ms per token, 303.93 tokens per second)
  3048. eval time = 9866.15 ms / 60 tokens ( 164.44 ms per token, 6.08 tokens per second)
  3049. total time = 10520.91 ms / 259 tokens
  3050. slot launch_slot_: id 1 | task 26974 | processing task
  3051. slot launch_slot_: id 18 | task 26976 | processing task
  3052. slot launch_slot_: id 28 | task 26977 | processing task
  3053. slot launch_slot_: id 29 | task 26978 | processing task
  3054. slot update_slots: id 42 | task 26932 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3055. slot update_slots: id 56 | task 26934 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3056. slot update_slots: id 60 | task 26936 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3057. slot update_slots: id 1 | task 26974 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3058. slot update_slots: id 1 | task 26974 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3059. slot update_slots: id 1 | task 26974 | kv cache rm [0, end)
  3060. slot update_slots: id 1 | task 26974 | prompt processing progress, n_past = 199, n_tokens = 259, progress = 1.000000
  3061. slot update_slots: id 1 | task 26974 | prompt done, n_past = 199, n_tokens = 259
  3062. slot update_slots: id 18 | task 26976 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3063. slot update_slots: id 18 | task 26976 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3064. slot update_slots: id 18 | task 26976 | kv cache rm [0, end)
  3065. slot update_slots: id 18 | task 26976 | prompt processing progress, n_past = 199, n_tokens = 458, progress = 1.000000
  3066. slot update_slots: id 18 | task 26976 | prompt done, n_past = 199, n_tokens = 458
  3067. slot update_slots: id 28 | task 26977 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3068. slot update_slots: id 28 | task 26977 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3069. slot update_slots: id 28 | task 26977 | kv cache rm [0, end)
  3070. slot update_slots: id 28 | task 26977 | prompt processing progress, n_past = 199, n_tokens = 657, progress = 1.000000
  3071. slot update_slots: id 28 | task 26977 | prompt done, n_past = 199, n_tokens = 657
  3072. slot update_slots: id 29 | task 26978 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3073. slot update_slots: id 29 | task 26978 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3074. slot update_slots: id 29 | task 26978 | kv cache rm [0, end)
  3075. slot update_slots: id 29 | task 26978 | prompt processing progress, n_past = 199, n_tokens = 856, progress = 1.000000
  3076. slot update_slots: id 29 | task 26978 | prompt done, n_past = 199, n_tokens = 856
  3077. srv cancel_tasks: cancel task, id_task = 27919
  3078. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3079. srv cancel_tasks: cancel task, id_task = 27920
  3080. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3081. slot update_slots: id 50 | task 26866 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3082. slot release: id 42 | task 26932 | stop processing: n_past = 131, truncated = 1
  3083. slot print_timing: id 42 | task 26932 |
  3084. prompt eval time = 342.67 ms / 199 tokens ( 1.72 ms per token, 580.73 tokens per second)
  3085. eval time = 9783.18 ms / 60 tokens ( 163.05 ms per token, 6.13 tokens per second)
  3086. total time = 10125.86 ms / 259 tokens
  3087. slot release: id 60 | task 26936 | stop processing: n_past = 131, truncated = 1
  3088. slot print_timing: id 60 | task 26936 |
  3089. prompt eval time = 344.04 ms / 199 tokens ( 1.73 ms per token, 578.41 tokens per second)
  3090. eval time = 9783.14 ms / 60 tokens ( 163.05 ms per token, 6.13 tokens per second)
  3091. total time = 10127.18 ms / 259 tokens
  3092. slot launch_slot_: id 42 | task 26981 | processing task
  3093. slot launch_slot_: id 60 | task 26983 | processing task
  3094. slot update_slots: id 36 | task 26869 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3095. slot update_slots: id 42 | task 26981 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3096. slot update_slots: id 42 | task 26981 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3097. slot update_slots: id 42 | task 26981 | kv cache rm [0, end)
  3098. slot update_slots: id 42 | task 26981 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3099. slot update_slots: id 42 | task 26981 | prompt done, n_past = 199, n_tokens = 261
  3100. slot update_slots: id 60 | task 26983 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3101. slot update_slots: id 60 | task 26983 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3102. slot update_slots: id 60 | task 26983 | kv cache rm [0, end)
  3103. slot update_slots: id 60 | task 26983 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3104. slot update_slots: id 60 | task 26983 | prompt done, n_past = 199, n_tokens = 460
  3105. srv cancel_tasks: cancel task, id_task = 27918
  3106. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3107. srv cancel_tasks: cancel task, id_task = 27923
  3108. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3109. slot update_slots: id 24 | task 26621 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3110. slot update_slots: id 41 | task 26937 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3111. slot release: id 41 | task 26937 | stop processing: n_past = 131, truncated = 1
  3112. slot print_timing: id 41 | task 26937 |
  3113. prompt eval time = 161.52 ms / 199 tokens ( 0.81 ms per token, 1232.02 tokens per second)
  3114. eval time = 9672.74 ms / 60 tokens ( 161.21 ms per token, 6.20 tokens per second)
  3115. total time = 9834.27 ms / 259 tokens
  3116. slot launch_slot_: id 41 | task 26984 | processing task
  3117. slot update_slots: id 41 | task 26984 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3118. slot update_slots: id 41 | task 26984 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3119. slot update_slots: id 41 | task 26984 | kv cache rm [0, end)
  3120. slot update_slots: id 41 | task 26984 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3121. slot update_slots: id 41 | task 26984 | prompt done, n_past = 199, n_tokens = 262
  3122. srv cancel_tasks: cancel task, id_task = 27929
  3123. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3124. srv cancel_tasks: cancel task, id_task = 27922
  3125. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3126. slot update_slots: id 14 | task 26627 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3127. slot update_slots: id 40 | task 26949 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3128. slot update_slots: id 13 | task 26877 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3129. slot update_slots: id 51 | task 26948 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3130. slot update_slots: id 21 | task 26951 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3131. slot release: id 21 | task 26951 | stop processing: n_past = 130, truncated = 1
  3132. slot print_timing: id 21 | task 26951 |
  3133. prompt eval time = 155.66 ms / 199 tokens ( 0.78 ms per token, 1278.45 tokens per second)
  3134. eval time = 9072.38 ms / 59 tokens ( 153.77 ms per token, 6.50 tokens per second)
  3135. total time = 9228.04 ms / 258 tokens
  3136. slot launch_slot_: id 21 | task 26985 | processing task
  3137. slot update_slots: id 21 | task 26985 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3138. slot update_slots: id 21 | task 26985 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3139. slot update_slots: id 21 | task 26985 | kv cache rm [0, end)
  3140. slot update_slots: id 21 | task 26985 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3141. slot update_slots: id 21 | task 26985 | prompt done, n_past = 199, n_tokens = 262
  3142. srv cancel_tasks: cancel task, id_task = 27945
  3143. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3144. srv cancel_tasks: cancel task, id_task = 27934
  3145. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3146. srv cancel_tasks: cancel task, id_task = 27947
  3147. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3148. slot update_slots: id 26 | task 26954 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3149. slot update_slots: id 52 | task 26742 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3150. slot update_slots: id 17 | task 26956 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3151. slot release: id 26 | task 26954 | stop processing: n_past = 131, truncated = 1
  3152. slot print_timing: id 26 | task 26954 |
  3153. prompt eval time = 159.90 ms / 199 tokens ( 0.80 ms per token, 1244.56 tokens per second)
  3154. eval time = 9363.16 ms / 60 tokens ( 156.05 ms per token, 6.41 tokens per second)
  3155. total time = 9523.05 ms / 259 tokens
  3156. slot launch_slot_: id 26 | task 26988 | processing task
  3157. slot update_slots: id 3 | task 26961 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3158. slot update_slots: id 20 | task 26965 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3159. slot update_slots: id 26 | task 26988 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3160. slot update_slots: id 26 | task 26988 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3161. slot update_slots: id 26 | task 26988 | kv cache rm [0, end)
  3162. slot update_slots: id 26 | task 26988 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3163. slot update_slots: id 26 | task 26988 | prompt done, n_past = 199, n_tokens = 262
  3164. slot release: id 17 | task 26956 | stop processing: n_past = 131, truncated = 1
  3165. slot print_timing: id 17 | task 26956 |
  3166. prompt eval time = 418.79 ms / 199 tokens ( 2.10 ms per token, 475.18 tokens per second)
  3167. eval time = 9103.58 ms / 60 tokens ( 151.73 ms per token, 6.59 tokens per second)
  3168. total time = 9522.36 ms / 259 tokens
  3169. slot launch_slot_: id 17 | task 26992 | processing task
  3170. slot update_slots: id 57 | task 26752 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3171. slot update_slots: id 17 | task 26992 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3172. slot update_slots: id 17 | task 26992 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3173. slot update_slots: id 17 | task 26992 | kv cache rm [0, end)
  3174. slot update_slots: id 17 | task 26992 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3175. slot update_slots: id 17 | task 26992 | prompt done, n_past = 199, n_tokens = 262
  3176. srv cancel_tasks: cancel task, id_task = 27933
  3177. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3178. slot release: id 20 | task 26965 | stop processing: n_past = 131, truncated = 1
  3179. slot print_timing: id 20 | task 26965 |
  3180. prompt eval time = 529.52 ms / 199 tokens ( 2.66 ms per token, 375.81 tokens per second)
  3181. eval time = 8782.08 ms / 60 tokens ( 146.37 ms per token, 6.83 tokens per second)
  3182. total time = 9311.60 ms / 259 tokens
  3183. slot launch_slot_: id 20 | task 26989 | processing task
  3184. slot update_slots: id 20 | task 26989 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3185. slot update_slots: id 20 | task 26989 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3186. slot update_slots: id 20 | task 26989 | kv cache rm [0, end)
  3187. slot update_slots: id 20 | task 26989 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3188. slot update_slots: id 20 | task 26989 | prompt done, n_past = 199, n_tokens = 262
  3189. slot update_slots: id 30 | task 26629 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3190. slot update_slots: id 39 | task 26966 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3191. slot update_slots: id 2 | task 26967 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3192. slot update_slots: id 6 | task 26605 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3193. srv cancel_tasks: cancel task, id_task = 27940
  3194. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3195. srv cancel_tasks: cancel task, id_task = 27937
  3196. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3197. slot update_slots: id 59 | task 26968 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3198. slot update_slots: id 43 | task 26653 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3199. slot release: id 2 | task 26967 | stop processing: n_past = 131, truncated = 1
  3200. slot print_timing: id 2 | task 26967 |
  3201. prompt eval time = 402.27 ms / 199 tokens ( 2.02 ms per token, 494.70 tokens per second)
  3202. eval time = 8237.66 ms / 60 tokens ( 137.29 ms per token, 7.28 tokens per second)
  3203. total time = 8639.92 ms / 259 tokens
  3204. slot launch_slot_: id 2 | task 26993 | processing task
  3205. slot update_slots: id 31 | task 26969 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3206. slot update_slots: id 2 | task 26993 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3207. slot update_slots: id 2 | task 26993 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3208. slot update_slots: id 2 | task 26993 | kv cache rm [0, end)
  3209. slot update_slots: id 2 | task 26993 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3210. slot update_slots: id 2 | task 26993 | prompt done, n_past = 199, n_tokens = 262
  3211. slot release: id 59 | task 26968 | stop processing: n_past = 131, truncated = 1
  3212. slot print_timing: id 59 | task 26968 |
  3213. prompt eval time = 425.59 ms / 199 tokens ( 2.14 ms per token, 467.58 tokens per second)
  3214. eval time = 7973.92 ms / 60 tokens ( 132.90 ms per token, 7.52 tokens per second)
  3215. total time = 8399.52 ms / 259 tokens
  3216. slot launch_slot_: id 59 | task 26994 | processing task
  3217. slot update_slots: id 59 | task 26994 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3218. slot update_slots: id 59 | task 26994 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3219. slot update_slots: id 59 | task 26994 | kv cache rm [0, end)
  3220. slot update_slots: id 59 | task 26994 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3221. slot update_slots: id 59 | task 26994 | prompt done, n_past = 199, n_tokens = 262
  3222. srv cancel_tasks: cancel task, id_task = 27944
  3223. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3224. srv cancel_tasks: cancel task, id_task = 27935
  3225. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3226. slot release: id 31 | task 26969 | stop processing: n_past = 131, truncated = 1
  3227. slot print_timing: id 31 | task 26969 |
  3228. prompt eval time = 147.99 ms / 199 tokens ( 0.74 ms per token, 1344.68 tokens per second)
  3229. eval time = 8277.79 ms / 60 tokens ( 137.96 ms per token, 7.25 tokens per second)
  3230. total time = 8425.78 ms / 259 tokens
  3231. slot release: id 58 | task 26923 | stop processing: n_past = 172, truncated = 1
  3232. slot print_timing: id 58 | task 26923 |
  3233. prompt eval time = 523.45 ms / 199 tokens ( 2.63 ms per token, 380.17 tokens per second)
  3234. eval time = 16742.41 ms / 101 tokens ( 165.77 ms per token, 6.03 tokens per second)
  3235. total time = 17265.85 ms / 300 tokens
  3236. slot launch_slot_: id 31 | task 26995 | processing task
  3237. slot launch_slot_: id 58 | task 26996 | processing task
  3238. slot update_slots: id 31 | task 26995 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3239. slot update_slots: id 31 | task 26995 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3240. slot update_slots: id 31 | task 26995 | kv cache rm [0, end)
  3241. slot update_slots: id 31 | task 26995 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3242. slot update_slots: id 31 | task 26995 | prompt done, n_past = 199, n_tokens = 261
  3243. slot update_slots: id 58 | task 26996 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3244. slot update_slots: id 58 | task 26996 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3245. slot update_slots: id 58 | task 26996 | kv cache rm [0, end)
  3246. slot update_slots: id 58 | task 26996 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3247. slot update_slots: id 58 | task 26996 | prompt done, n_past = 199, n_tokens = 460
  3248. slot update_slots: id 19 | task 26483 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3249. slot update_slots: id 22 | task 26488 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3250. slot update_slots: id 23 | task 26535 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3251. slot update_slots: id 25 | task 26512 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3252. slot update_slots: id 35 | task 26522 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3253. slot update_slots: id 37 | task 26484 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3254. slot update_slots: id 48 | task 26498 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3255. slot update_slots: id 53 | task 26776 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3256. slot update_slots: id 54 | task 26525 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3257. srv cancel_tasks: cancel task, id_task = 27941
  3258. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3259. slot release: id 56 | task 26934 | stop processing: n_past = 172, truncated = 1
  3260. slot print_timing: id 56 | task 26934 |
  3261. prompt eval time = 343.76 ms / 199 tokens ( 1.73 ms per token, 578.89 tokens per second)
  3262. eval time = 16370.12 ms / 101 tokens ( 162.08 ms per token, 6.17 tokens per second)
  3263. total time = 16713.88 ms / 300 tokens
  3264. slot launch_slot_: id 56 | task 26997 | processing task
  3265. slot update_slots: id 56 | task 26997 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3266. slot update_slots: id 56 | task 26997 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3267. slot update_slots: id 56 | task 26997 | kv cache rm [0, end)
  3268. slot update_slots: id 56 | task 26997 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3269. slot update_slots: id 56 | task 26997 | prompt done, n_past = 199, n_tokens = 262
  3270. slot update_slots: id 46 | task 26895 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3271. srv cancel_tasks: cancel task, id_task = 27948
  3272. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3273. srv cancel_tasks: cancel task, id_task = 27939
  3274. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3275. slot update_slots: id 12 | task 26970 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3276. slot update_slots: id 7 | task 26972 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3277. slot release: id 12 | task 26970 | stop processing: n_past = 131, truncated = 1
  3278. slot print_timing: id 12 | task 26970 |
  3279. prompt eval time = 152.67 ms / 199 tokens ( 0.77 ms per token, 1303.46 tokens per second)
  3280. eval time = 9856.74 ms / 60 tokens ( 164.28 ms per token, 6.09 tokens per second)
  3281. total time = 10009.41 ms / 259 tokens
  3282. slot launch_slot_: id 12 | task 26990 | processing task
  3283. slot update_slots: id 12 | task 26990 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3284. slot update_slots: id 12 | task 26990 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3285. slot update_slots: id 12 | task 26990 | kv cache rm [0, end)
  3286. slot update_slots: id 12 | task 26990 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3287. slot update_slots: id 12 | task 26990 | prompt done, n_past = 199, n_tokens = 262
  3288. slot release: id 7 | task 26972 | stop processing: n_past = 131, truncated = 1
  3289. slot print_timing: id 7 | task 26972 |
  3290. prompt eval time = 159.27 ms / 199 tokens ( 0.80 ms per token, 1249.42 tokens per second)
  3291. eval time = 9842.47 ms / 60 tokens ( 164.04 ms per token, 6.10 tokens per second)
  3292. total time = 10001.75 ms / 259 tokens
  3293. slot launch_slot_: id 7 | task 27000 | processing task
  3294. slot update_slots: id 7 | task 27000 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3295. slot update_slots: id 7 | task 27000 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3296. slot update_slots: id 7 | task 27000 | kv cache rm [0, end)
  3297. slot update_slots: id 7 | task 27000 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3298. slot update_slots: id 7 | task 27000 | prompt done, n_past = 199, n_tokens = 262
  3299. slot update_slots: id 63 | task 26973 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3300. slot update_slots: id 1 | task 26974 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3301. slot update_slots: id 18 | task 26976 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3302. slot update_slots: id 28 | task 26977 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3303. slot update_slots: id 29 | task 26978 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3304. srv cancel_tasks: cancel task, id_task = 27946
  3305. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3306. slot release: id 29 | task 26978 | stop processing: n_past = 130, truncated = 1
  3307. slot print_timing: id 29 | task 26978 |
  3308. prompt eval time = 444.96 ms / 199 tokens ( 2.24 ms per token, 447.23 tokens per second)
  3309. eval time = 9350.06 ms / 59 tokens ( 158.48 ms per token, 6.31 tokens per second)
  3310. total time = 9795.02 ms / 258 tokens
  3311. slot release: id 40 | task 26949 | stop processing: n_past = 172, truncated = 1
  3312. slot print_timing: id 40 | task 26949 |
  3313. prompt eval time = 157.37 ms / 199 tokens ( 0.79 ms per token, 1264.54 tokens per second)
  3314. eval time = 16603.12 ms / 101 tokens ( 164.39 ms per token, 6.08 tokens per second)
  3315. total time = 16760.49 ms / 300 tokens
  3316. slot launch_slot_: id 29 | task 27004 | processing task
  3317. slot launch_slot_: id 40 | task 27005 | processing task
  3318. slot update_slots: id 29 | task 27004 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3319. slot update_slots: id 29 | task 27004 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3320. slot update_slots: id 29 | task 27004 | kv cache rm [0, end)
  3321. slot update_slots: id 29 | task 27004 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3322. slot update_slots: id 29 | task 27004 | prompt done, n_past = 199, n_tokens = 261
  3323. slot update_slots: id 40 | task 27005 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3324. slot update_slots: id 40 | task 27005 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3325. slot update_slots: id 40 | task 27005 | kv cache rm [0, end)
  3326. slot update_slots: id 40 | task 27005 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3327. slot update_slots: id 40 | task 27005 | prompt done, n_past = 199, n_tokens = 460
  3328. slot release: id 1 | task 26974 | stop processing: n_past = 131, truncated = 1
  3329. slot print_timing: id 1 | task 26974 |
  3330. prompt eval time = 443.07 ms / 199 tokens ( 2.23 ms per token, 449.14 tokens per second)
  3331. eval time = 9584.85 ms / 60 tokens ( 159.75 ms per token, 6.26 tokens per second)
  3332. total time = 10027.91 ms / 259 tokens
  3333. slot release: id 18 | task 26976 | stop processing: n_past = 131, truncated = 1
  3334. slot print_timing: id 18 | task 26976 |
  3335. prompt eval time = 444.30 ms / 199 tokens ( 2.23 ms per token, 447.90 tokens per second)
  3336. eval time = 9584.91 ms / 60 tokens ( 159.75 ms per token, 6.26 tokens per second)
  3337. total time = 10029.21 ms / 259 tokens
  3338. slot launch_slot_: id 1 | task 27008 | processing task
  3339. slot launch_slot_: id 18 | task 27009 | processing task
  3340. slot update_slots: id 42 | task 26981 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3341. slot update_slots: id 60 | task 26983 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3342. slot update_slots: id 1 | task 27008 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3343. slot update_slots: id 1 | task 27008 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3344. slot update_slots: id 1 | task 27008 | kv cache rm [0, end)
  3345. slot update_slots: id 1 | task 27008 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3346. slot update_slots: id 1 | task 27008 | prompt done, n_past = 199, n_tokens = 261
  3347. slot update_slots: id 18 | task 27009 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3348. slot update_slots: id 18 | task 27009 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3349. slot update_slots: id 18 | task 27009 | kv cache rm [0, end)
  3350. slot update_slots: id 18 | task 27009 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3351. slot update_slots: id 18 | task 27009 | prompt done, n_past = 199, n_tokens = 460
  3352. srv cancel_tasks: cancel task, id_task = 27942
  3353. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3354. slot release: id 42 | task 26981 | stop processing: n_past = 130, truncated = 1
  3355. slot print_timing: id 42 | task 26981 |
  3356. prompt eval time = 408.21 ms / 199 tokens ( 2.05 ms per token, 487.49 tokens per second)
  3357. eval time = 9348.29 ms / 59 tokens ( 158.45 ms per token, 6.31 tokens per second)
  3358. total time = 9756.51 ms / 258 tokens
  3359. slot launch_slot_: id 42 | task 27006 | processing task
  3360. slot update_slots: id 42 | task 27006 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3361. slot update_slots: id 42 | task 27006 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3362. slot update_slots: id 42 | task 27006 | kv cache rm [0, end)
  3363. slot update_slots: id 42 | task 27006 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3364. slot update_slots: id 42 | task 27006 | prompt done, n_past = 199, n_tokens = 262
  3365. slot update_slots: id 4 | task 26792 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3366. slot update_slots: id 15 | task 26795 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3367. srv cancel_tasks: cancel task, id_task = 27950
  3368. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3369. srv cancel_tasks: cancel task, id_task = 27949
  3370. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3371. srv cancel_tasks: cancel task, id_task = 27962
  3372. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3373. slot update_slots: id 11 | task 26813 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3374. slot update_slots: id 41 | task 26984 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3375. slot release: id 41 | task 26984 | stop processing: n_past = 131, truncated = 1
  3376. slot print_timing: id 41 | task 26984 |
  3377. prompt eval time = 158.99 ms / 199 tokens ( 0.80 ms per token, 1251.62 tokens per second)
  3378. eval time = 9576.53 ms / 60 tokens ( 159.61 ms per token, 6.27 tokens per second)
  3379. total time = 9735.53 ms / 259 tokens
  3380. slot launch_slot_: id 41 | task 27010 | processing task
  3381. slot update_slots: id 47 | task 26903 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3382. slot update_slots: id 55 | task 26686 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3383. slot update_slots: id 41 | task 27010 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3384. slot update_slots: id 41 | task 27010 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3385. slot update_slots: id 41 | task 27010 | kv cache rm [0, end)
  3386. slot update_slots: id 41 | task 27010 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3387. slot update_slots: id 41 | task 27010 | prompt done, n_past = 199, n_tokens = 262
  3388. slot update_slots: id 8 | task 26904 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3389. srv cancel_tasks: cancel task, id_task = 27951
  3390. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3391. slot update_slots: id 10 | task 26821 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3392. slot update_slots: id 21 | task 26985 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3393. slot update_slots: id 45 | task 26908 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3394. slot update_slots: id 5 | task 26905 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3395. slot release: id 21 | task 26985 | stop processing: n_past = 131, truncated = 1
  3396. slot print_timing: id 21 | task 26985 |
  3397. prompt eval time = 159.84 ms / 199 tokens ( 0.80 ms per token, 1244.99 tokens per second)
  3398. eval time = 9789.43 ms / 60 tokens ( 163.16 ms per token, 6.13 tokens per second)
  3399. total time = 9949.27 ms / 259 tokens
  3400. slot launch_slot_: id 21 | task 27011 | processing task
  3401. slot update_slots: id 21 | task 27011 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3402. slot update_slots: id 21 | task 27011 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3403. slot update_slots: id 21 | task 27011 | kv cache rm [0, end)
  3404. slot update_slots: id 21 | task 27011 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3405. slot update_slots: id 21 | task 27011 | prompt done, n_past = 199, n_tokens = 262
  3406. srv cancel_tasks: cancel task, id_task = 27957
  3407. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3408. slot update_slots: id 9 | task 26823 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3409. slot update_slots: id 26 | task 26988 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3410. slot release: id 51 | task 26948 | stop processing: n_past = 194, truncated = 1
  3411. slot print_timing: id 51 | task 26948 |
  3412. prompt eval time = 155.12 ms / 199 tokens ( 0.78 ms per token, 1282.91 tokens per second)
  3413. eval time = 19644.44 ms / 123 tokens ( 159.71 ms per token, 6.26 tokens per second)
  3414. total time = 19799.55 ms / 322 tokens
  3415. slot launch_slot_: id 51 | task 27012 | processing task
  3416. slot update_slots: id 17 | task 26992 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3417. slot update_slots: id 51 | task 27012 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3418. slot update_slots: id 51 | task 27012 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3419. slot update_slots: id 51 | task 27012 | kv cache rm [0, end)
  3420. slot update_slots: id 51 | task 27012 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3421. slot update_slots: id 51 | task 27012 | prompt done, n_past = 199, n_tokens = 262
  3422. slot release: id 26 | task 26988 | stop processing: n_past = 131, truncated = 1
  3423. slot print_timing: id 26 | task 26988 |
  3424. prompt eval time = 161.22 ms / 199 tokens ( 0.81 ms per token, 1234.35 tokens per second)
  3425. eval time = 9914.66 ms / 60 tokens ( 165.24 ms per token, 6.05 tokens per second)
  3426. total time = 10075.88 ms / 259 tokens
  3427. slot launch_slot_: id 26 | task 27013 | processing task
  3428. slot update_slots: id 20 | task 26989 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3429. slot update_slots: id 26 | task 27013 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3430. slot update_slots: id 26 | task 27013 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3431. slot update_slots: id 26 | task 27013 | kv cache rm [0, end)
  3432. slot update_slots: id 26 | task 27013 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3433. slot update_slots: id 26 | task 27013 | prompt done, n_past = 199, n_tokens = 262
  3434. slot release: id 17 | task 26992 | stop processing: n_past = 131, truncated = 1
  3435. slot print_timing: id 17 | task 26992 |
  3436. prompt eval time = 329.88 ms / 199 tokens ( 1.66 ms per token, 603.25 tokens per second)
  3437. eval time = 9741.43 ms / 60 tokens ( 162.36 ms per token, 6.16 tokens per second)
  3438. total time = 10071.31 ms / 259 tokens
  3439. slot launch_slot_: id 17 | task 27014 | processing task
  3440. slot update_slots: id 17 | task 27014 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3441. slot update_slots: id 17 | task 27014 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3442. slot update_slots: id 17 | task 27014 | kv cache rm [0, end)
  3443. slot update_slots: id 17 | task 27014 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3444. slot update_slots: id 17 | task 27014 | prompt done, n_past = 199, n_tokens = 262
  3445. srv cancel_tasks: cancel task, id_task = 27959
  3446. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3447. srv cancel_tasks: cancel task, id_task = 27958
  3448. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3449. slot release: id 3 | task 26961 | stop processing: n_past = 194, truncated = 1
  3450. slot print_timing: id 3 | task 26961 |
  3451. prompt eval time = 528.33 ms / 199 tokens ( 2.65 ms per token, 376.66 tokens per second)
  3452. eval time = 19011.69 ms / 123 tokens ( 154.57 ms per token, 6.47 tokens per second)
  3453. total time = 19540.02 ms / 322 tokens
  3454. slot launch_slot_: id 3 | task 27015 | processing task
  3455. slot update_slots: id 0 | task 26700 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3456. slot update_slots: id 2 | task 26993 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3457. slot update_slots: id 3 | task 27015 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3458. slot update_slots: id 3 | task 27015 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3459. slot update_slots: id 3 | task 27015 | kv cache rm [0, end)
  3460. slot update_slots: id 3 | task 27015 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3461. slot update_slots: id 3 | task 27015 | prompt done, n_past = 199, n_tokens = 262
  3462. slot update_slots: id 59 | task 26994 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3463. srv cancel_tasks: cancel task, id_task = 27960
  3464. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3465. srv cancel_tasks: cancel task, id_task = 27961
  3466. srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
  3467. slot release: id 2 | task 26993 | stop processing: n_past = 131, truncated = 1
  3468. slot print_timing: id 2 | task 26993 |
  3469. prompt eval time = 157.22 ms / 199 tokens ( 0.79 ms per token, 1265.78 tokens per second)
  3470. eval time = 9440.86 ms / 60 tokens ( 157.35 ms per token, 6.36 tokens per second)
  3471. total time = 9598.08 ms / 259 tokens
  3472. slot launch_slot_: id 2 | task 27016 | processing task
  3473. slot update_slots: id 31 | task 26995 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3474. slot update_slots: id 49 | task 26713 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3475. slot update_slots: id 58 | task 26996 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3476. slot update_slots: id 61 | task 26715 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3477. slot update_slots: id 2 | task 27016 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3478. slot update_slots: id 2 | task 27016 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3479. slot update_slots: id 2 | task 27016 | kv cache rm [0, end)
  3480. slot update_slots: id 2 | task 27016 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3481. slot update_slots: id 2 | task 27016 | prompt done, n_past = 199, n_tokens = 262
  3482. slot update_slots: id 32 | task 26846 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3483. slot update_slots: id 56 | task 26997 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3484. slot update_slots: id 16 | task 26582 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3485. slot update_slots: id 38 | task 26598 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3486. slot update_slots: id 44 | task 26608 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3487. slot update_slots: id 62 | task 26614 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3488. slot update_slots: id 12 | task 26990 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3489. slot update_slots: id 27 | task 26919 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3490. slot update_slots: id 7 | task 27000 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3491. slot update_slots: id 33 | task 26851 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3492. slot release: id 12 | task 26990 | stop processing: n_past = 131, truncated = 1
  3493. slot print_timing: id 12 | task 26990 |
  3494. prompt eval time = 148.87 ms / 199 tokens ( 0.75 ms per token, 1336.72 tokens per second)
  3495. eval time = 8079.57 ms / 60 tokens ( 134.66 ms per token, 7.43 tokens per second)
  3496. total time = 8228.44 ms / 259 tokens
  3497. slot launch_slot_: id 12 | task 27021 | processing task
  3498. slot update_slots: id 12 | task 27021 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3499. slot update_slots: id 12 | task 27021 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3500. slot update_slots: id 12 | task 27021 | kv cache rm [0, end)
  3501. slot update_slots: id 12 | task 27021 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3502. slot update_slots: id 12 | task 27021 | prompt done, n_past = 199, n_tokens = 262
  3503. slot release: id 7 | task 27000 | stop processing: n_past = 131, truncated = 1
  3504. slot print_timing: id 7 | task 27000 |
  3505. prompt eval time = 150.96 ms / 199 tokens ( 0.76 ms per token, 1318.20 tokens per second)
  3506. eval time = 8247.51 ms / 60 tokens ( 137.46 ms per token, 7.27 tokens per second)
  3507. total time = 8398.48 ms / 259 tokens
  3508. slot launch_slot_: id 7 | task 27022 | processing task
  3509. slot update_slots: id 7 | task 27022 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3510. slot update_slots: id 7 | task 27022 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3511. slot update_slots: id 7 | task 27022 | kv cache rm [0, end)
  3512. slot update_slots: id 7 | task 27022 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3513. slot update_slots: id 7 | task 27022 | prompt done, n_past = 199, n_tokens = 262
  3514. slot update_slots: id 29 | task 27004 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3515. slot update_slots: id 40 | task 27005 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3516. slot update_slots: id 1 | task 27008 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3517. slot update_slots: id 18 | task 27009 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3518. slot release: id 29 | task 27004 | stop processing: n_past = 131, truncated = 1
  3519. slot print_timing: id 29 | task 27004 |
  3520. prompt eval time = 231.17 ms / 199 tokens ( 1.16 ms per token, 860.84 tokens per second)
  3521. eval time = 7844.59 ms / 60 tokens ( 130.74 ms per token, 7.65 tokens per second)
  3522. total time = 8075.76 ms / 259 tokens
  3523. slot launch_slot_: id 29 | task 27023 | processing task
  3524. slot update_slots: id 42 | task 27006 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3525. slot update_slots: id 29 | task 27023 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3526. slot update_slots: id 29 | task 27023 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3527. slot update_slots: id 29 | task 27023 | kv cache rm [0, end)
  3528. slot update_slots: id 29 | task 27023 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3529. slot update_slots: id 29 | task 27023 | prompt done, n_past = 199, n_tokens = 262
  3530. slot release: id 1 | task 27008 | stop processing: n_past = 131, truncated = 1
  3531. slot print_timing: id 1 | task 27008 |
  3532. prompt eval time = 400.65 ms / 199 tokens ( 2.01 ms per token, 496.69 tokens per second)
  3533. eval time = 7594.81 ms / 60 tokens ( 126.58 ms per token, 7.90 tokens per second)
  3534. total time = 7995.47 ms / 259 tokens
  3535. slot release: id 18 | task 27009 | stop processing: n_past = 131, truncated = 1
  3536. slot print_timing: id 18 | task 27009 |
  3537. prompt eval time = 401.90 ms / 199 tokens ( 2.02 ms per token, 495.14 tokens per second)
  3538. eval time = 7594.97 ms / 60 tokens ( 126.58 ms per token, 7.90 tokens per second)
  3539. total time = 7996.88 ms / 259 tokens
  3540. slot launch_slot_: id 1 | task 27024 | processing task
  3541. slot launch_slot_: id 18 | task 27025 | processing task
  3542. slot update_slots: id 1 | task 27024 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3543. slot update_slots: id 1 | task 27024 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3544. slot update_slots: id 1 | task 27024 | kv cache rm [0, end)
  3545. slot update_slots: id 1 | task 27024 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3546. slot update_slots: id 1 | task 27024 | prompt done, n_past = 199, n_tokens = 261
  3547. slot update_slots: id 18 | task 27025 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3548. slot update_slots: id 18 | task 27025 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3549. slot update_slots: id 18 | task 27025 | kv cache rm [0, end)
  3550. slot update_slots: id 18 | task 27025 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3551. slot update_slots: id 18 | task 27025 | prompt done, n_past = 199, n_tokens = 460
  3552. slot release: id 42 | task 27006 | stop processing: n_past = 130, truncated = 1
  3553. slot print_timing: id 42 | task 27006 |
  3554. prompt eval time = 153.56 ms / 199 tokens ( 0.77 ms per token, 1295.94 tokens per second)
  3555. eval time = 7624.58 ms / 59 tokens ( 129.23 ms per token, 7.74 tokens per second)
  3556. total time = 7778.13 ms / 258 tokens
  3557. slot launch_slot_: id 42 | task 27026 | processing task
  3558. slot update_slots: id 42 | task 27026 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3559. slot update_slots: id 42 | task 27026 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3560. slot update_slots: id 42 | task 27026 | kv cache rm [0, end)
  3561. slot update_slots: id 42 | task 27026 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3562. slot update_slots: id 42 | task 27026 | prompt done, n_past = 199, n_tokens = 262
  3563. slot release: id 63 | task 26973 | stop processing: n_past = 194, truncated = 1
  3564. slot print_timing: id 63 | task 26973 |
  3565. prompt eval time = 155.86 ms / 199 tokens ( 0.78 ms per token, 1276.78 tokens per second)
  3566. eval time = 18598.17 ms / 123 tokens ( 151.20 ms per token, 6.61 tokens per second)
  3567. total time = 18754.04 ms / 322 tokens
  3568. slot launch_slot_: id 63 | task 27028 | processing task
  3569. slot update_slots: id 34 | task 26922 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3570. slot update_slots: id 63 | task 27028 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3571. slot update_slots: id 63 | task 27028 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3572. slot update_slots: id 63 | task 27028 | kv cache rm [0, end)
  3573. slot update_slots: id 63 | task 27028 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3574. slot update_slots: id 63 | task 27028 | prompt done, n_past = 199, n_tokens = 262
  3575. slot release: id 60 | task 26983 | stop processing: n_past = 194, truncated = 1
  3576. slot print_timing: id 60 | task 26983 |
  3577. prompt eval time = 409.63 ms / 199 tokens ( 2.06 ms per token, 485.80 tokens per second)
  3578. eval time = 17940.37 ms / 123 tokens ( 145.86 ms per token, 6.86 tokens per second)
  3579. total time = 18350.00 ms / 322 tokens
  3580. slot launch_slot_: id 60 | task 27032 | processing task
  3581. slot update_slots: id 60 | task 27032 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3582. slot update_slots: id 60 | task 27032 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3583. slot update_slots: id 60 | task 27032 | kv cache rm [0, end)
  3584. slot update_slots: id 60 | task 27032 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3585. slot update_slots: id 60 | task 27032 | prompt done, n_past = 199, n_tokens = 262
  3586. slot update_slots: id 50 | task 26866 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3587. slot update_slots: id 36 | task 26869 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3588. slot update_slots: id 41 | task 27010 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3589. slot release: id 28 | task 26977 | stop processing: n_past = 203, truncated = 1
  3590. slot print_timing: id 28 | task 26977 |
  3591. prompt eval time = 444.97 ms / 199 tokens ( 2.24 ms per token, 447.22 tokens per second)
  3592. eval time = 19607.03 ms / 132 tokens ( 148.54 ms per token, 6.73 tokens per second)
  3593. total time = 20052.00 ms / 331 tokens
  3594. slot launch_slot_: id 28 | task 27033 | processing task
  3595. slot update_slots: id 28 | task 27033 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3596. slot update_slots: id 28 | task 27033 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3597. slot update_slots: id 28 | task 27033 | kv cache rm [0, end)
  3598. slot update_slots: id 28 | task 27033 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3599. slot update_slots: id 28 | task 27033 | prompt done, n_past = 199, n_tokens = 262
  3600. slot release: id 41 | task 27010 | stop processing: n_past = 131, truncated = 1
  3601. slot print_timing: id 41 | task 27010 |
  3602. prompt eval time = 158.54 ms / 199 tokens ( 0.80 ms per token, 1255.17 tokens per second)
  3603. eval time = 8339.88 ms / 60 tokens ( 139.00 ms per token, 7.19 tokens per second)
  3604. total time = 8498.42 ms / 259 tokens
  3605. slot launch_slot_: id 41 | task 27034 | processing task
  3606. slot update_slots: id 41 | task 27034 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3607. slot update_slots: id 41 | task 27034 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3608. slot update_slots: id 41 | task 27034 | kv cache rm [0, end)
  3609. slot update_slots: id 41 | task 27034 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3610. slot update_slots: id 41 | task 27034 | prompt done, n_past = 199, n_tokens = 262
  3611. slot update_slots: id 24 | task 26621 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3612. slot update_slots: id 21 | task 27011 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3613. slot release: id 31 | task 26995 | stop processing: n_past = 172, truncated = 1
  3614. slot print_timing: id 31 | task 26995 |
  3615. prompt eval time = 240.26 ms / 199 tokens ( 1.21 ms per token, 828.27 tokens per second)
  3616. eval time = 14890.79 ms / 101 tokens ( 147.43 ms per token, 6.78 tokens per second)
  3617. total time = 15131.05 ms / 300 tokens
  3618. slot launch_slot_: id 31 | task 27039 | processing task
  3619. slot update_slots: id 31 | task 27039 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3620. slot update_slots: id 31 | task 27039 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3621. slot update_slots: id 31 | task 27039 | kv cache rm [0, end)
  3622. slot update_slots: id 31 | task 27039 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3623. slot update_slots: id 31 | task 27039 | prompt done, n_past = 199, n_tokens = 262
  3624. slot update_slots: id 14 | task 26627 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3625. slot update_slots: id 51 | task 27012 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3626. slot release: id 56 | task 26997 | stop processing: n_past = 172, truncated = 1
  3627. slot print_timing: id 56 | task 26997 |
  3628. prompt eval time = 377.81 ms / 199 tokens ( 1.90 ms per token, 526.72 tokens per second)
  3629. eval time = 14171.34 ms / 101 tokens ( 140.31 ms per token, 7.13 tokens per second)
  3630. total time = 14549.16 ms / 300 tokens
  3631. slot launch_slot_: id 56 | task 27046 | processing task
  3632. slot update_slots: id 26 | task 27013 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3633. slot update_slots: id 56 | task 27046 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3634. slot update_slots: id 56 | task 27046 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3635. slot update_slots: id 56 | task 27046 | kv cache rm [0, end)
  3636. slot update_slots: id 56 | task 27046 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3637. slot update_slots: id 56 | task 27046 | prompt done, n_past = 199, n_tokens = 262
  3638. slot update_slots: id 17 | task 27014 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3639. slot update_slots: id 13 | task 26877 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3640. slot release: id 26 | task 27013 | stop processing: n_past = 131, truncated = 1
  3641. slot print_timing: id 26 | task 27013 |
  3642. prompt eval time = 157.18 ms / 199 tokens ( 0.79 ms per token, 1266.10 tokens per second)
  3643. eval time = 8849.03 ms / 60 tokens ( 147.48 ms per token, 6.78 tokens per second)
  3644. total time = 9006.20 ms / 259 tokens
  3645. slot launch_slot_: id 26 | task 27047 | processing task
  3646. slot update_slots: id 26 | task 27047 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3647. slot update_slots: id 26 | task 27047 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3648. slot update_slots: id 26 | task 27047 | kv cache rm [0, end)
  3649. slot update_slots: id 26 | task 27047 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3650. slot update_slots: id 26 | task 27047 | prompt done, n_past = 199, n_tokens = 262
  3651. slot update_slots: id 3 | task 27015 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3652. slot update_slots: id 52 | task 26742 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3653. slot release: id 3 | task 27015 | stop processing: n_past = 131, truncated = 1
  3654. slot print_timing: id 3 | task 27015 |
  3655. prompt eval time = 155.94 ms / 199 tokens ( 0.78 ms per token, 1276.12 tokens per second)
  3656. eval time = 8672.22 ms / 60 tokens ( 144.54 ms per token, 6.92 tokens per second)
  3657. total time = 8828.16 ms / 259 tokens
  3658. slot release: id 20 | task 26989 | stop processing: n_past = 194, truncated = 1
  3659. slot print_timing: id 20 | task 26989 |
  3660. prompt eval time = 155.50 ms / 199 tokens ( 0.78 ms per token, 1279.78 tokens per second)
  3661. eval time = 18903.83 ms / 123 tokens ( 153.69 ms per token, 6.51 tokens per second)
  3662. total time = 19059.32 ms / 322 tokens
  3663. slot launch_slot_: id 3 | task 27048 | processing task
  3664. slot launch_slot_: id 20 | task 27049 | processing task
  3665. slot update_slots: id 2 | task 27016 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3666. slot update_slots: id 3 | task 27048 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3667. slot update_slots: id 3 | task 27048 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3668. slot update_slots: id 3 | task 27048 | kv cache rm [0, end)
  3669. slot update_slots: id 3 | task 27048 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3670. slot update_slots: id 3 | task 27048 | prompt done, n_past = 199, n_tokens = 261
  3671. slot update_slots: id 20 | task 27049 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3672. slot update_slots: id 20 | task 27049 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3673. slot update_slots: id 20 | task 27049 | kv cache rm [0, end)
  3674. slot update_slots: id 20 | task 27049 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3675. slot update_slots: id 20 | task 27049 | prompt done, n_past = 199, n_tokens = 460
  3676. slot update_slots: id 57 | task 26752 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3677. slot release: id 2 | task 27016 | stop processing: n_past = 131, truncated = 1
  3678. slot print_timing: id 2 | task 27016 |
  3679. prompt eval time = 155.91 ms / 199 tokens ( 0.78 ms per token, 1276.42 tokens per second)
  3680. eval time = 8845.40 ms / 60 tokens ( 147.42 ms per token, 6.78 tokens per second)
  3681. total time = 9001.30 ms / 259 tokens
  3682. slot launch_slot_: id 2 | task 27050 | processing task
  3683. slot update_slots: id 2 | task 27050 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3684. slot update_slots: id 2 | task 27050 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3685. slot update_slots: id 2 | task 27050 | kv cache rm [0, end)
  3686. slot update_slots: id 2 | task 27050 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3687. slot update_slots: id 2 | task 27050 | prompt done, n_past = 199, n_tokens = 262
  3688. slot update_slots: id 30 | task 26629 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3689. slot update_slots: id 39 | task 26966 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3690. slot update_slots: id 6 | task 26605 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3691. slot update_slots: id 43 | task 26653 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3692. slot update_slots: id 19 | task 26483 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3693. slot update_slots: id 22 | task 26488 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3694. slot update_slots: id 23 | task 26535 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3695. slot update_slots: id 25 | task 26512 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3696. slot update_slots: id 35 | task 26522 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3697. slot update_slots: id 37 | task 26484 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3698. slot update_slots: id 48 | task 26498 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3699. slot update_slots: id 53 | task 26776 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3700. slot update_slots: id 54 | task 26525 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3701. slot release: id 22 | task 26488 | stop processing: n_past = 130, truncated = 1
  3702. slot print_timing: id 22 | task 26488 |
  3703. prompt eval time = 1696.41 ms / 1 tokens ( 1696.41 ms per token, 0.59 tokens per second)
  3704. eval time = 120753.73 ms / 694 tokens ( 174.00 ms per token, 5.75 tokens per second)
  3705. total time = 122450.14 ms / 695 tokens
  3706. slot release: id 59 | task 26994 | stop processing: n_past = 203, truncated = 1
  3707. slot print_timing: id 59 | task 26994 |
  3708. prompt eval time = 452.45 ms / 199 tokens ( 2.27 ms per token, 439.82 tokens per second)
  3709. eval time = 19659.24 ms / 132 tokens ( 148.93 ms per token, 6.71 tokens per second)
  3710. total time = 20111.70 ms / 331 tokens
  3711. slot launch_slot_: id 22 | task 27051 | processing task
  3712. slot launch_slot_: id 59 | task 27052 | processing task
  3713. slot update_slots: id 12 | task 27021 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3714. slot update_slots: id 22 | task 27051 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3715. slot update_slots: id 22 | task 27051 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3716. slot update_slots: id 22 | task 27051 | kv cache rm [0, end)
  3717. slot update_slots: id 22 | task 27051 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3718. slot update_slots: id 22 | task 27051 | prompt done, n_past = 199, n_tokens = 261
  3719. slot update_slots: id 59 | task 27052 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3720. slot update_slots: id 59 | task 27052 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3721. slot update_slots: id 59 | task 27052 | kv cache rm [0, end)
  3722. slot update_slots: id 59 | task 27052 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3723. slot update_slots: id 59 | task 27052 | prompt done, n_past = 199, n_tokens = 460
  3724. slot release: id 58 | task 26996 | stop processing: n_past = 203, truncated = 1
  3725. slot print_timing: id 58 | task 26996 |
  3726. prompt eval time = 242.38 ms / 199 tokens ( 1.22 ms per token, 821.01 tokens per second)
  3727. eval time = 20002.60 ms / 132 tokens ( 151.53 ms per token, 6.60 tokens per second)
  3728. total time = 20244.99 ms / 331 tokens
  3729. slot launch_slot_: id 58 | task 27053 | processing task
  3730. slot update_slots: id 7 | task 27022 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3731. slot update_slots: id 58 | task 27053 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3732. slot update_slots: id 58 | task 27053 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3733. slot update_slots: id 58 | task 27053 | kv cache rm [0, end)
  3734. slot update_slots: id 58 | task 27053 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3735. slot update_slots: id 58 | task 27053 | prompt done, n_past = 199, n_tokens = 262
  3736. slot update_slots: id 46 | task 26895 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3737. slot release: id 7 | task 27022 | stop processing: n_past = 131, truncated = 1
  3738. slot print_timing: id 7 | task 27022 |
  3739. prompt eval time = 149.33 ms / 199 tokens ( 0.75 ms per token, 1332.62 tokens per second)
  3740. eval time = 9764.40 ms / 60 tokens ( 162.74 ms per token, 6.14 tokens per second)
  3741. total time = 9913.73 ms / 259 tokens
  3742. slot launch_slot_: id 7 | task 27058 | processing task
  3743. slot update_slots: id 7 | task 27058 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3744. slot update_slots: id 7 | task 27058 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3745. slot update_slots: id 7 | task 27058 | kv cache rm [0, end)
  3746. slot update_slots: id 7 | task 27058 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3747. slot update_slots: id 7 | task 27058 | prompt done, n_past = 199, n_tokens = 262
  3748. slot update_slots: id 29 | task 27023 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3749. slot update_slots: id 1 | task 27024 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3750. slot update_slots: id 18 | task 27025 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3751. slot update_slots: id 42 | task 27026 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3752. slot update_slots: id 63 | task 27028 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3753. slot release: id 1 | task 27024 | stop processing: n_past = 131, truncated = 1
  3754. slot print_timing: id 1 | task 27024 |
  3755. prompt eval time = 403.37 ms / 199 tokens ( 2.03 ms per token, 493.34 tokens per second)
  3756. eval time = 9411.40 ms / 60 tokens ( 156.86 ms per token, 6.38 tokens per second)
  3757. total time = 9814.77 ms / 259 tokens
  3758. slot launch_slot_: id 1 | task 27057 | processing task
  3759. slot update_slots: id 1 | task 27057 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3760. slot update_slots: id 1 | task 27057 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3761. slot update_slots: id 1 | task 27057 | kv cache rm [0, end)
  3762. slot update_slots: id 1 | task 27057 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3763. slot update_slots: id 1 | task 27057 | prompt done, n_past = 199, n_tokens = 262
  3764. slot release: id 42 | task 27026 | stop processing: n_past = 131, truncated = 1
  3765. slot print_timing: id 42 | task 27026 |
  3766. prompt eval time = 153.01 ms / 199 tokens ( 0.77 ms per token, 1300.54 tokens per second)
  3767. eval time = 9408.41 ms / 60 tokens ( 156.81 ms per token, 6.38 tokens per second)
  3768. total time = 9561.42 ms / 259 tokens
  3769. slot launch_slot_: id 42 | task 27063 | processing task
  3770. slot update_slots: id 42 | task 27063 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3771. slot update_slots: id 42 | task 27063 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3772. slot update_slots: id 42 | task 27063 | kv cache rm [0, end)
  3773. slot update_slots: id 42 | task 27063 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3774. slot update_slots: id 42 | task 27063 | prompt done, n_past = 199, n_tokens = 262
  3775. slot release: id 63 | task 27028 | stop processing: n_past = 131, truncated = 1
  3776. slot print_timing: id 63 | task 27028 |
  3777. prompt eval time = 325.14 ms / 199 tokens ( 1.63 ms per token, 612.05 tokens per second)
  3778. eval time = 9236.60 ms / 60 tokens ( 153.94 ms per token, 6.50 tokens per second)
  3779. total time = 9561.74 ms / 259 tokens
  3780. slot launch_slot_: id 63 | task 27062 | processing task
  3781. slot update_slots: id 63 | task 27062 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3782. slot update_slots: id 63 | task 27062 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3783. slot update_slots: id 63 | task 27062 | kv cache rm [0, end)
  3784. slot update_slots: id 63 | task 27062 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3785. slot update_slots: id 63 | task 27062 | prompt done, n_past = 199, n_tokens = 262
  3786. slot update_slots: id 60 | task 27032 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3787. slot update_slots: id 28 | task 27033 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3788. slot update_slots: id 41 | task 27034 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3789. slot update_slots: id 4 | task 26792 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3790. slot update_slots: id 15 | task 26795 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3791. slot release: id 28 | task 27033 | stop processing: n_past = 131, truncated = 1
  3792. slot print_timing: id 28 | task 27033 |
  3793. prompt eval time = 153.05 ms / 199 tokens ( 0.77 ms per token, 1300.22 tokens per second)
  3794. eval time = 8929.33 ms / 60 tokens ( 148.82 ms per token, 6.72 tokens per second)
  3795. total time = 9082.39 ms / 259 tokens
  3796. slot launch_slot_: id 28 | task 27064 | processing task
  3797. slot update_slots: id 28 | task 27064 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3798. slot update_slots: id 28 | task 27064 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3799. slot update_slots: id 28 | task 27064 | kv cache rm [0, end)
  3800. slot update_slots: id 28 | task 27064 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3801. slot update_slots: id 28 | task 27064 | prompt done, n_past = 199, n_tokens = 262
  3802. slot update_slots: id 11 | task 26813 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3803. slot release: id 40 | task 27005 | stop processing: n_past = 210, truncated = 1
  3804. slot print_timing: id 40 | task 27005 |
  3805. prompt eval time = 231.86 ms / 199 tokens ( 1.17 ms per token, 858.27 tokens per second)
  3806. eval time = 19926.58 ms / 139 tokens ( 143.36 ms per token, 6.98 tokens per second)
  3807. total time = 20158.45 ms / 338 tokens
  3808. slot launch_slot_: id 40 | task 27065 | processing task
  3809. slot update_slots: id 31 | task 27039 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3810. slot update_slots: id 40 | task 27065 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3811. slot update_slots: id 40 | task 27065 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3812. slot update_slots: id 40 | task 27065 | kv cache rm [0, end)
  3813. slot update_slots: id 40 | task 27065 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3814. slot update_slots: id 40 | task 27065 | prompt done, n_past = 199, n_tokens = 262
  3815. slot release: id 12 | task 27021 | stop processing: n_past = 157, truncated = 1
  3816. slot print_timing: id 12 | task 27021 |
  3817. prompt eval time = 317.27 ms / 199 tokens ( 1.59 ms per token, 627.23 tokens per second)
  3818. eval time = 12951.89 ms / 86 tokens ( 150.60 ms per token, 6.64 tokens per second)
  3819. total time = 13269.16 ms / 285 tokens
  3820. slot launch_slot_: id 12 | task 27066 | processing task
  3821. slot update_slots: id 12 | task 27066 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3822. slot update_slots: id 12 | task 27066 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3823. slot update_slots: id 12 | task 27066 | kv cache rm [0, end)
  3824. slot update_slots: id 12 | task 27066 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3825. slot update_slots: id 12 | task 27066 | prompt done, n_past = 199, n_tokens = 262
  3826. slot update_slots: id 47 | task 26903 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3827. slot update_slots: id 55 | task 26686 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3828. slot release: id 31 | task 27039 | stop processing: n_past = 131, truncated = 1
  3829. slot print_timing: id 31 | task 27039 |
  3830. prompt eval time = 156.26 ms / 199 tokens ( 0.79 ms per token, 1273.52 tokens per second)
  3831. eval time = 9155.59 ms / 60 tokens ( 152.59 ms per token, 6.55 tokens per second)
  3832. total time = 9311.85 ms / 259 tokens
  3833. slot launch_slot_: id 31 | task 27067 | processing task
  3834. slot update_slots: id 8 | task 26904 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3835. slot update_slots: id 31 | task 27067 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3836. slot update_slots: id 31 | task 27067 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3837. slot update_slots: id 31 | task 27067 | kv cache rm [0, end)
  3838. slot update_slots: id 31 | task 27067 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3839. slot update_slots: id 31 | task 27067 | prompt done, n_past = 199, n_tokens = 262
  3840. slot update_slots: id 56 | task 27046 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3841. slot release: id 56 | task 27046 | stop processing: n_past = 131, truncated = 1
  3842. slot print_timing: id 56 | task 27046 |
  3843. prompt eval time = 164.10 ms / 199 tokens ( 0.82 ms per token, 1212.70 tokens per second)
  3844. eval time = 9334.54 ms / 60 tokens ( 155.58 ms per token, 6.43 tokens per second)
  3845. total time = 9498.64 ms / 259 tokens
  3846. slot launch_slot_: id 56 | task 27072 | processing task
  3847. slot update_slots: id 26 | task 27047 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3848. slot update_slots: id 56 | task 27072 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3849. slot update_slots: id 56 | task 27072 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3850. slot update_slots: id 56 | task 27072 | kv cache rm [0, end)
  3851. slot update_slots: id 56 | task 27072 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3852. slot update_slots: id 56 | task 27072 | prompt done, n_past = 199, n_tokens = 262
  3853. slot update_slots: id 10 | task 26821 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3854. slot release: id 26 | task 27047 | stop processing: n_past = 131, truncated = 1
  3855. slot print_timing: id 26 | task 27047 |
  3856. prompt eval time = 155.48 ms / 199 tokens ( 0.78 ms per token, 1279.88 tokens per second)
  3857. eval time = 9077.03 ms / 60 tokens ( 151.28 ms per token, 6.61 tokens per second)
  3858. total time = 9232.51 ms / 259 tokens
  3859. slot launch_slot_: id 26 | task 27073 | processing task
  3860. slot update_slots: id 45 | task 26908 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3861. slot update_slots: id 26 | task 27073 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3862. slot update_slots: id 26 | task 27073 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3863. slot update_slots: id 26 | task 27073 | kv cache rm [0, end)
  3864. slot update_slots: id 26 | task 27073 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3865. slot update_slots: id 26 | task 27073 | prompt done, n_past = 199, n_tokens = 262
  3866. slot update_slots: id 5 | task 26905 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3867. slot update_slots: id 3 | task 27048 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3868. slot update_slots: id 20 | task 27049 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3869. slot release: id 29 | task 27023 | stop processing: n_past = 164, truncated = 1
  3870. slot print_timing: id 29 | task 27023 |
  3871. prompt eval time = 153.35 ms / 199 tokens ( 0.77 ms per token, 1297.66 tokens per second)
  3872. eval time = 15054.80 ms / 93 tokens ( 161.88 ms per token, 6.18 tokens per second)
  3873. total time = 15208.15 ms / 292 tokens
  3874. slot launch_slot_: id 29 | task 27074 | processing task
  3875. slot update_slots: id 9 | task 26823 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3876. slot update_slots: id 29 | task 27074 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3877. slot update_slots: id 29 | task 27074 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3878. slot update_slots: id 29 | task 27074 | kv cache rm [0, end)
  3879. slot update_slots: id 29 | task 27074 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3880. slot update_slots: id 29 | task 27074 | prompt done, n_past = 199, n_tokens = 262
  3881. slot release: id 3 | task 27048 | stop processing: n_past = 131, truncated = 1
  3882. slot print_timing: id 3 | task 27048 |
  3883. prompt eval time = 241.02 ms / 199 tokens ( 1.21 ms per token, 825.65 tokens per second)
  3884. eval time = 9764.40 ms / 60 tokens ( 162.74 ms per token, 6.14 tokens per second)
  3885. total time = 10005.42 ms / 259 tokens
  3886. slot release: id 20 | task 27049 | stop processing: n_past = 131, truncated = 1
  3887. slot print_timing: id 20 | task 27049 |
  3888. prompt eval time = 242.24 ms / 199 tokens ( 1.22 ms per token, 821.52 tokens per second)
  3889. eval time = 9764.61 ms / 60 tokens ( 162.74 ms per token, 6.14 tokens per second)
  3890. total time = 10006.84 ms / 259 tokens
  3891. slot release: id 21 | task 27011 | stop processing: n_past = 202, truncated = 1
  3892. slot print_timing: id 21 | task 27011 |
  3893. prompt eval time = 152.41 ms / 199 tokens ( 0.77 ms per token, 1305.71 tokens per second)
  3894. eval time = 20480.83 ms / 131 tokens ( 156.34 ms per token, 6.40 tokens per second)
  3895. total time = 20633.24 ms / 330 tokens
  3896. slot launch_slot_: id 3 | task 27075 | processing task
  3897. slot launch_slot_: id 20 | task 27079 | processing task
  3898. slot launch_slot_: id 21 | task 27080 | processing task
  3899. slot update_slots: id 2 | task 27050 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3900. slot update_slots: id 3 | task 27075 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3901. slot update_slots: id 3 | task 27075 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3902. slot update_slots: id 3 | task 27075 | kv cache rm [0, end)
  3903. slot update_slots: id 3 | task 27075 | prompt processing progress, n_past = 199, n_tokens = 260, progress = 1.000000
  3904. slot update_slots: id 3 | task 27075 | prompt done, n_past = 199, n_tokens = 260
  3905. slot update_slots: id 20 | task 27079 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3906. slot update_slots: id 20 | task 27079 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3907. slot update_slots: id 20 | task 27079 | kv cache rm [0, end)
  3908. slot update_slots: id 20 | task 27079 | prompt processing progress, n_past = 199, n_tokens = 459, progress = 1.000000
  3909. slot update_slots: id 20 | task 27079 | prompt done, n_past = 199, n_tokens = 459
  3910. slot update_slots: id 21 | task 27080 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3911. slot update_slots: id 21 | task 27080 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3912. slot update_slots: id 21 | task 27080 | kv cache rm [0, end)
  3913. slot update_slots: id 21 | task 27080 | prompt processing progress, n_past = 199, n_tokens = 658, progress = 1.000000
  3914. slot update_slots: id 21 | task 27080 | prompt done, n_past = 199, n_tokens = 658
  3915. slot release: id 2 | task 27050 | stop processing: n_past = 131, truncated = 1
  3916. slot print_timing: id 2 | task 27050 |
  3917. prompt eval time = 462.52 ms / 199 tokens ( 2.32 ms per token, 430.25 tokens per second)
  3918. eval time = 10002.27 ms / 60 tokens ( 166.70 ms per token, 6.00 tokens per second)
  3919. total time = 10464.79 ms / 259 tokens
  3920. slot launch_slot_: id 2 | task 27082 | processing task
  3921. slot update_slots: id 2 | task 27082 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3922. slot update_slots: id 2 | task 27082 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3923. slot update_slots: id 2 | task 27082 | kv cache rm [0, end)
  3924. slot update_slots: id 2 | task 27082 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3925. slot update_slots: id 2 | task 27082 | prompt done, n_past = 199, n_tokens = 262
  3926. slot release: id 18 | task 27025 | stop processing: n_past = 172, truncated = 1
  3927. slot print_timing: id 18 | task 27025 |
  3928. prompt eval time = 404.77 ms / 199 tokens ( 2.03 ms per token, 491.64 tokens per second)
  3929. eval time = 16506.38 ms / 101 tokens ( 163.43 ms per token, 6.12 tokens per second)
  3930. total time = 16911.14 ms / 300 tokens
  3931. slot launch_slot_: id 18 | task 27088 | processing task
  3932. slot update_slots: id 0 | task 26700 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3933. slot update_slots: id 18 | task 27088 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3934. slot update_slots: id 18 | task 27088 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3935. slot update_slots: id 18 | task 27088 | kv cache rm [0, end)
  3936. slot update_slots: id 18 | task 27088 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3937. slot update_slots: id 18 | task 27088 | prompt done, n_past = 199, n_tokens = 262
  3938. slot update_slots: id 49 | task 26713 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3939. slot update_slots: id 61 | task 26715 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3940. slot update_slots: id 32 | task 26846 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3941. slot release: id 51 | task 27012 | stop processing: n_past = 212, truncated = 1
  3942. slot print_timing: id 51 | task 27012 |
  3943. prompt eval time = 159.87 ms / 199 tokens ( 0.80 ms per token, 1244.73 tokens per second)
  3944. eval time = 22327.81 ms / 141 tokens ( 158.35 ms per token, 6.31 tokens per second)
  3945. total time = 22487.68 ms / 340 tokens
  3946. slot release: id 60 | task 27032 | stop processing: n_past = 172, truncated = 1
  3947. slot print_timing: id 60 | task 27032 |
  3948. prompt eval time = 153.41 ms / 199 tokens ( 0.77 ms per token, 1297.14 tokens per second)
  3949. eval time = 16459.57 ms / 101 tokens ( 162.97 ms per token, 6.14 tokens per second)
  3950. total time = 16612.99 ms / 300 tokens
  3951. slot launch_slot_: id 51 | task 27093 | processing task
  3952. slot launch_slot_: id 60 | task 27094 | processing task
  3953. slot update_slots: id 22 | task 27051 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3954. slot update_slots: id 59 | task 27052 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3955. slot update_slots: id 51 | task 27093 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3956. slot update_slots: id 51 | task 27093 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3957. slot update_slots: id 51 | task 27093 | kv cache rm [0, end)
  3958. slot update_slots: id 51 | task 27093 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3959. slot update_slots: id 51 | task 27093 | prompt done, n_past = 199, n_tokens = 261
  3960. slot update_slots: id 60 | task 27094 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3961. slot update_slots: id 60 | task 27094 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3962. slot update_slots: id 60 | task 27094 | kv cache rm [0, end)
  3963. slot update_slots: id 60 | task 27094 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  3964. slot update_slots: id 60 | task 27094 | prompt done, n_past = 199, n_tokens = 460
  3965. slot release: id 22 | task 27051 | stop processing: n_past = 130, truncated = 1
  3966. slot print_timing: id 22 | task 27051 |
  3967. prompt eval time = 407.07 ms / 199 tokens ( 2.05 ms per token, 488.86 tokens per second)
  3968. eval time = 10094.44 ms / 59 tokens ( 171.09 ms per token, 5.84 tokens per second)
  3969. total time = 10501.51 ms / 258 tokens
  3970. slot launch_slot_: id 22 | task 27097 | processing task
  3971. slot update_slots: id 16 | task 26582 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3972. slot update_slots: id 58 | task 27053 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3973. slot update_slots: id 22 | task 27097 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3974. slot update_slots: id 22 | task 27097 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3975. slot update_slots: id 22 | task 27097 | kv cache rm [0, end)
  3976. slot update_slots: id 22 | task 27097 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  3977. slot update_slots: id 22 | task 27097 | prompt done, n_past = 199, n_tokens = 262
  3978. slot release: id 17 | task 27014 | stop processing: n_past = 212, truncated = 1
  3979. slot print_timing: id 17 | task 27014 |
  3980. prompt eval time = 328.62 ms / 199 tokens ( 1.65 ms per token, 605.57 tokens per second)
  3981. eval time = 22376.85 ms / 141 tokens ( 158.70 ms per token, 6.30 tokens per second)
  3982. total time = 22705.47 ms / 340 tokens
  3983. slot release: id 59 | task 27052 | stop processing: n_past = 131, truncated = 1
  3984. slot print_timing: id 59 | task 27052 |
  3985. prompt eval time = 410.06 ms / 199 tokens ( 2.06 ms per token, 485.29 tokens per second)
  3986. eval time = 10478.62 ms / 60 tokens ( 174.64 ms per token, 5.73 tokens per second)
  3987. total time = 10888.68 ms / 259 tokens
  3988. slot launch_slot_: id 17 | task 27098 | processing task
  3989. slot launch_slot_: id 59 | task 27100 | processing task
  3990. slot update_slots: id 38 | task 26598 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3991. slot update_slots: id 44 | task 26608 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  3992. slot update_slots: id 17 | task 27098 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3993. slot update_slots: id 17 | task 27098 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3994. slot update_slots: id 17 | task 27098 | kv cache rm [0, end)
  3995. slot update_slots: id 17 | task 27098 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  3996. slot update_slots: id 17 | task 27098 | prompt done, n_past = 199, n_tokens = 261
  3997. slot update_slots: id 59 | task 27100 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  3998. slot update_slots: id 59 | task 27100 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  3999. slot update_slots: id 59 | task 27100 | kv cache rm [0, end)
  4000. slot update_slots: id 59 | task 27100 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  4001. slot update_slots: id 59 | task 27100 | prompt done, n_past = 199, n_tokens = 460
  4002. slot update_slots: id 62 | task 26614 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4003. slot release: id 58 | task 27053 | stop processing: n_past = 131, truncated = 1
  4004. slot print_timing: id 58 | task 27053 |
  4005. prompt eval time = 329.27 ms / 199 tokens ( 1.65 ms per token, 604.36 tokens per second)
  4006. eval time = 10602.07 ms / 60 tokens ( 176.70 ms per token, 5.66 tokens per second)
  4007. total time = 10931.35 ms / 259 tokens
  4008. slot launch_slot_: id 58 | task 27102 | processing task
  4009. slot update_slots: id 7 | task 27058 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4010. slot update_slots: id 58 | task 27102 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4011. slot update_slots: id 58 | task 27102 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4012. slot update_slots: id 58 | task 27102 | kv cache rm [0, end)
  4013. slot update_slots: id 58 | task 27102 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4014. slot update_slots: id 58 | task 27102 | prompt done, n_past = 199, n_tokens = 262
  4015. slot release: id 7 | task 27058 | stop processing: n_past = 131, truncated = 1
  4016. slot print_timing: id 7 | task 27058 |
  4017. prompt eval time = 148.56 ms / 199 tokens ( 0.75 ms per token, 1339.57 tokens per second)
  4018. eval time = 10714.82 ms / 60 tokens ( 178.58 ms per token, 5.60 tokens per second)
  4019. total time = 10863.38 ms / 259 tokens
  4020. slot launch_slot_: id 7 | task 27103 | processing task
  4021. slot update_slots: id 7 | task 27103 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4022. slot update_slots: id 7 | task 27103 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4023. slot update_slots: id 7 | task 27103 | kv cache rm [0, end)
  4024. slot update_slots: id 7 | task 27103 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4025. slot update_slots: id 7 | task 27103 | prompt done, n_past = 199, n_tokens = 262
  4026. slot update_slots: id 1 | task 27057 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4027. slot update_slots: id 27 | task 26919 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4028. slot update_slots: id 42 | task 27063 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4029. slot update_slots: id 33 | task 26851 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4030. slot update_slots: id 63 | task 27062 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4031. slot release: id 1 | task 27057 | stop processing: n_past = 131, truncated = 1
  4032. slot print_timing: id 1 | task 27057 |
  4033. prompt eval time = 146.90 ms / 199 tokens ( 0.74 ms per token, 1354.70 tokens per second)
  4034. eval time = 10602.70 ms / 60 tokens ( 176.71 ms per token, 5.66 tokens per second)
  4035. total time = 10749.60 ms / 259 tokens
  4036. slot launch_slot_: id 1 | task 27105 | processing task
  4037. slot update_slots: id 1 | task 27105 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4038. slot update_slots: id 1 | task 27105 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4039. slot update_slots: id 1 | task 27105 | kv cache rm [0, end)
  4040. slot update_slots: id 1 | task 27105 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4041. slot update_slots: id 1 | task 27105 | prompt done, n_past = 199, n_tokens = 262
  4042. slot release: id 63 | task 27062 | stop processing: n_past = 131, truncated = 1
  4043. slot print_timing: id 63 | task 27062 |
  4044. prompt eval time = 322.56 ms / 199 tokens ( 1.62 ms per token, 616.93 tokens per second)
  4045. eval time = 10491.87 ms / 60 tokens ( 174.86 ms per token, 5.72 tokens per second)
  4046. total time = 10814.43 ms / 259 tokens
  4047. slot launch_slot_: id 63 | task 27107 | processing task
  4048. slot update_slots: id 63 | task 27107 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4049. slot update_slots: id 63 | task 27107 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4050. slot update_slots: id 63 | task 27107 | kv cache rm [0, end)
  4051. slot update_slots: id 63 | task 27107 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4052. slot update_slots: id 63 | task 27107 | prompt done, n_past = 199, n_tokens = 262
  4053. slot update_slots: id 28 | task 27064 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4054. slot update_slots: id 34 | task 26922 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4055. slot release: id 28 | task 27064 | stop processing: n_past = 131, truncated = 1
  4056. slot print_timing: id 28 | task 27064 |
  4057. prompt eval time = 368.78 ms / 199 tokens ( 1.85 ms per token, 539.61 tokens per second)
  4058. eval time = 10276.33 ms / 60 tokens ( 171.27 ms per token, 5.84 tokens per second)
  4059. total time = 10645.11 ms / 259 tokens
  4060. slot launch_slot_: id 28 | task 27110 | processing task
  4061. slot update_slots: id 28 | task 27110 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4062. slot update_slots: id 28 | task 27110 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4063. slot update_slots: id 28 | task 27110 | kv cache rm [0, end)
  4064. slot update_slots: id 28 | task 27110 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4065. slot update_slots: id 28 | task 27110 | prompt done, n_past = 199, n_tokens = 262
  4066. slot update_slots: id 40 | task 27065 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4067. slot update_slots: id 50 | task 26866 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4068. slot update_slots: id 12 | task 27066 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4069. slot update_slots: id 36 | task 26869 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4070. slot release: id 40 | task 27065 | stop processing: n_past = 131, truncated = 1
  4071. slot print_timing: id 40 | task 27065 |
  4072. prompt eval time = 157.14 ms / 199 tokens ( 0.79 ms per token, 1266.39 tokens per second)
  4073. eval time = 10280.34 ms / 60 tokens ( 171.34 ms per token, 5.84 tokens per second)
  4074. total time = 10437.48 ms / 259 tokens
  4075. slot launch_slot_: id 40 | task 27112 | processing task
  4076. slot update_slots: id 31 | task 27067 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4077. slot update_slots: id 40 | task 27112 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4078. slot update_slots: id 40 | task 27112 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4079. slot update_slots: id 40 | task 27112 | kv cache rm [0, end)
  4080. slot update_slots: id 40 | task 27112 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4081. slot update_slots: id 40 | task 27112 | prompt done, n_past = 199, n_tokens = 262
  4082. slot release: id 31 | task 27067 | stop processing: n_past = 131, truncated = 1
  4083. slot print_timing: id 31 | task 27067 |
  4084. prompt eval time = 433.16 ms / 199 tokens ( 2.18 ms per token, 459.41 tokens per second)
  4085. eval time = 9788.50 ms / 60 tokens ( 163.14 ms per token, 6.13 tokens per second)
  4086. total time = 10221.66 ms / 259 tokens
  4087. slot release: id 41 | task 27034 | stop processing: n_past = 199, truncated = 1
  4088. slot print_timing: id 41 | task 27034 |
  4089. prompt eval time = 369.30 ms / 199 tokens ( 1.86 ms per token, 538.86 tokens per second)
  4090. eval time = 20307.83 ms / 128 tokens ( 158.65 ms per token, 6.30 tokens per second)
  4091. total time = 20677.13 ms / 327 tokens
  4092. slot launch_slot_: id 31 | task 27133 | processing task
  4093. slot launch_slot_: id 41 | task 27134 | processing task
  4094. slot update_slots: id 31 | task 27133 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4095. slot update_slots: id 31 | task 27133 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4096. slot update_slots: id 31 | task 27133 | kv cache rm [0, end)
  4097. slot update_slots: id 31 | task 27133 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  4098. slot update_slots: id 31 | task 27133 | prompt done, n_past = 199, n_tokens = 261
  4099. slot update_slots: id 41 | task 27134 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4100. slot update_slots: id 41 | task 27134 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4101. slot update_slots: id 41 | task 27134 | kv cache rm [0, end)
  4102. slot update_slots: id 41 | task 27134 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  4103. slot update_slots: id 41 | task 27134 | prompt done, n_past = 199, n_tokens = 460
  4104. slot update_slots: id 56 | task 27072 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4105. slot update_slots: id 24 | task 26621 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4106. slot release: id 56 | task 27072 | stop processing: n_past = 131, truncated = 1
  4107. slot print_timing: id 56 | task 27072 |
  4108. prompt eval time = 159.04 ms / 199 tokens ( 0.80 ms per token, 1251.27 tokens per second)
  4109. eval time = 10330.18 ms / 60 tokens ( 172.17 ms per token, 5.81 tokens per second)
  4110. total time = 10489.22 ms / 259 tokens
  4111. slot launch_slot_: id 56 | task 27139 | processing task
  4112. slot update_slots: id 26 | task 27073 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4113. slot update_slots: id 56 | task 27139 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4114. slot update_slots: id 56 | task 27139 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4115. slot update_slots: id 56 | task 27139 | kv cache rm [0, end)
  4116. slot update_slots: id 56 | task 27139 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4117. slot update_slots: id 56 | task 27139 | prompt done, n_past = 199, n_tokens = 262
  4118. slot release: id 26 | task 27073 | stop processing: n_past = 131, truncated = 1
  4119. slot print_timing: id 26 | task 27073 |
  4120. prompt eval time = 157.12 ms / 199 tokens ( 0.79 ms per token, 1266.55 tokens per second)
  4121. eval time = 10325.87 ms / 60 tokens ( 172.10 ms per token, 5.81 tokens per second)
  4122. total time = 10482.99 ms / 259 tokens
  4123. slot launch_slot_: id 26 | task 27140 | processing task
  4124. slot update_slots: id 26 | task 27140 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4125. slot update_slots: id 26 | task 27140 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4126. slot update_slots: id 26 | task 27140 | kv cache rm [0, end)
  4127. slot update_slots: id 26 | task 27140 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4128. slot update_slots: id 26 | task 27140 | prompt done, n_past = 199, n_tokens = 262
  4129. slot update_slots: id 14 | task 26627 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4130. slot update_slots: id 29 | task 27074 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4131. slot update_slots: id 3 | task 27075 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4132. slot update_slots: id 20 | task 27079 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4133. slot update_slots: id 21 | task 27080 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4134. slot release: id 29 | task 27074 | stop processing: n_past = 131, truncated = 1
  4135. slot print_timing: id 29 | task 27074 |
  4136. prompt eval time = 155.77 ms / 199 tokens ( 0.78 ms per token, 1277.55 tokens per second)
  4137. eval time = 9941.09 ms / 60 tokens ( 165.68 ms per token, 6.04 tokens per second)
  4138. total time = 10096.86 ms / 259 tokens
  4139. slot launch_slot_: id 29 | task 27141 | processing task
  4140. slot update_slots: id 29 | task 27141 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4141. slot update_slots: id 29 | task 27141 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4142. slot update_slots: id 29 | task 27141 | kv cache rm [0, end)
  4143. slot update_slots: id 29 | task 27141 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4144. slot update_slots: id 29 | task 27141 | prompt done, n_past = 199, n_tokens = 262
  4145. slot release: id 20 | task 27079 | stop processing: n_past = 131, truncated = 1
  4146. slot print_timing: id 20 | task 27079 |
  4147. prompt eval time = 343.21 ms / 199 tokens ( 1.72 ms per token, 579.82 tokens per second)
  4148. eval time = 10094.66 ms / 60 tokens ( 168.24 ms per token, 5.94 tokens per second)
  4149. total time = 10437.87 ms / 259 tokens
  4150. slot release: id 21 | task 27080 | stop processing: n_past = 131, truncated = 1
  4151. slot print_timing: id 21 | task 27080 |
  4152. prompt eval time = 343.22 ms / 199 tokens ( 1.72 ms per token, 579.80 tokens per second)
  4153. eval time = 10094.71 ms / 60 tokens ( 168.25 ms per token, 5.94 tokens per second)
  4154. total time = 10437.93 ms / 259 tokens
  4155. slot launch_slot_: id 20 | task 27142 | processing task
  4156. slot launch_slot_: id 21 | task 27145 | processing task
  4157. slot update_slots: id 2 | task 27082 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4158. slot update_slots: id 13 | task 26877 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4159. slot update_slots: id 20 | task 27142 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4160. slot update_slots: id 20 | task 27142 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4161. slot update_slots: id 20 | task 27142 | kv cache rm [0, end)
  4162. slot update_slots: id 20 | task 27142 | prompt processing progress, n_past = 199, n_tokens = 261, progress = 1.000000
  4163. slot update_slots: id 20 | task 27142 | prompt done, n_past = 199, n_tokens = 261
  4164. slot update_slots: id 21 | task 27145 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4165. slot update_slots: id 21 | task 27145 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4166. slot update_slots: id 21 | task 27145 | kv cache rm [0, end)
  4167. slot update_slots: id 21 | task 27145 | prompt processing progress, n_past = 199, n_tokens = 460, progress = 1.000000
  4168. slot update_slots: id 21 | task 27145 | prompt done, n_past = 199, n_tokens = 460
  4169. slot release: id 2 | task 27082 | stop processing: n_past = 131, truncated = 1
  4170. slot print_timing: id 2 | task 27082 |
  4171. prompt eval time = 150.92 ms / 199 tokens ( 0.76 ms per token, 1318.60 tokens per second)
  4172. eval time = 9825.65 ms / 60 tokens ( 163.76 ms per token, 6.11 tokens per second)
  4173. total time = 9976.57 ms / 259 tokens
  4174. slot launch_slot_: id 2 | task 27164 | processing task
  4175. slot update_slots: id 2 | task 27164 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4176. slot update_slots: id 2 | task 27164 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4177. slot update_slots: id 2 | task 27164 | kv cache rm [0, end)
  4178. slot update_slots: id 2 | task 27164 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4179. slot update_slots: id 2 | task 27164 | prompt done, n_past = 199, n_tokens = 262
  4180. slot update_slots: id 18 | task 27088 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4181. slot update_slots: id 52 | task 26742 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4182. slot release: id 52 | task 26742 | stop processing: n_past = 130, truncated = 1
  4183. slot print_timing: id 52 | task 26742 |
  4184. prompt eval time = 546.30 ms / 199 tokens ( 2.75 ms per token, 364.27 tokens per second)
  4185. eval time = 96523.40 ms / 567 tokens ( 170.24 ms per token, 5.87 tokens per second)
  4186. total time = 97069.70 ms / 766 tokens
  4187. slot launch_slot_: id 52 | task 27167 | processing task
  4188. slot update_slots: id 52 | task 27167 | new prompt, n_ctx_slot = 256, n_keep = 0, n_prompt_tokens = 8007
  4189. slot update_slots: id 52 | task 27167 | input truncated, n_ctx = 256, n_keep = 0, n_left = 256, n_prompt_tokens = 199
  4190. slot update_slots: id 52 | task 27167 | kv cache rm [0, end)
  4191. slot update_slots: id 52 | task 27167 | prompt processing progress, n_past = 199, n_tokens = 262, progress = 1.000000
  4192. slot update_slots: id 52 | task 27167 | prompt done, n_past = 199, n_tokens = 262
  4193. slot update_slots: id 57 | task 26752 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4194. slot update_slots: id 51 | task 27093 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4195. slot update_slots: id 60 | task 27094 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4196. slot update_slots: id 22 | task 27097 | slot context shift, n_keep = 0, n_left = 255, n_discard = 127
  4197. slot release: id 51 | task 27093 | stop processing: n_past = 131, truncated = 1
  4198. slot print_timing: id 51 | task 27093 |
  4199. prompt eval time = 243.72 ms / 199 tokens ( 1.22 ms per token, 816.51 tokens per second)
  4200. eval time = 10145.84 ms / 60 tokens ( 169.10 ms per token, 5.91 tokens per second)
  4201. total time = 10389.56 ms / 259 tokens
Tags: llama.cpp
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement