API tools faq
paste
Guest User

MTP

a guest
Jun 8th, 2026
50
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 25.86 KB | None | 0 0
raw download clone embed print report
  1. You are a helpful assistant<|im_end|>
  2. <|im_start|>user
  3. Hello<|im_end|>
  4. <|im_start|>assistant
  5. Hi there<|im_end|>
  6. <|im_start|>user
  7. How are you?<|im_end|>
  8. <|im_start|>assistant
  9. <think>
  10. '
  11. 0.29.134.079 I srv init: init: chat template, thinking = 1
  12. 0.29.134.146 I srv llama_server: model loaded
  13. 0.29.134.149 I srv llama_server: server is listening on http://127.0.0.1:8080
  14. 0.29.134.165 I srv update_slots: all slots are idle
  15. 1.54.766.781 I srv params_from_: Chat format: peg-native
  16. 1.54.799.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
  17. 1.54.799.839 I srv get_availabl: updating prompt cache
  18. 1.54.799.852 I srv load: - looking for better prompt, base f_keep = -1.000, sim = 0.000
  19. 1.54.799.855 I srv update: - cache state: 0 prompts, 0.000 MiB (limits: 8192.000 MiB, 160000 tokens, 8589934592 est)
  20. 1.54.799.857 I srv get_availabl: prompt cache update took 0.02 ms
  21. 1.54.800.996 I reasoning-budget: activated, budget=2147483647 tokens
  22. 1.54.801.035 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0
  23. 1.58.343.598 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 6144, progress = 0.29, t = 3.54 s / 1734.45 tokens per second
  24. 1.59.399.717 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 8192, progress = 0.38, t = 4.60 s / 1781.49 tokens per second
  25. 2.00.473.441 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 10240, progress = 0.48, t = 5.67 s / 1805.34 tokens per second
  26. 2.01.566.808 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 12288, progress = 0.57, t = 6.77 s / 1816.31 tokens per second
  27. 2.02.687.888 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 14336, progress = 0.67, t = 7.89 s / 1817.82 tokens per second
  28. 2.03.847.493 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 16384, progress = 0.76, t = 9.05 s / 1811.20 tokens per second
  29. 2.05.031.745 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 18432, progress = 0.86, t = 10.23 s / 1801.74 tokens per second
  30. 2.06.233.341 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 20480, progress = 0.95, t = 11.43 s / 1791.52 tokens per second
  31. 2.06.417.546 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 20648, progress = 0.96, t = 11.62 s / 1777.57 tokens per second
  32. 2.06.494.514 I slot create_check: id 0 | task 0 | created context checkpoint 1 of 32 (pos_min = 20647, pos_max = 20647, n_tokens = 20648, size = 192.869 MiB)
  33. 2.06.817.141 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 20995, progress = 0.98, t = 12.02 s / 1747.34 tokens per second
  34. 2.07.241.141 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 21507, progress = 1.00, t = 12.44 s / 1728.95 tokens per second
  35. 2.08.242.640 I reasoning-budget: deactivated (natural end)
  36. 2.08.689.806 I slot print_timing: id 0 | task 0 | prompt eval time = 12531.30 ms / 21511 tokens ( 0.58 ms per token, 1716.58 tokens per second)
  37. 2.08.689.812 I slot print_timing: id 0 | task 0 | eval time = 1356.29 ms / 84 tokens ( 16.15 ms per token, 61.93 tokens per second)
  38. 2.08.689.813 I slot print_timing: id 0 | task 0 | total time = 13887.60 ms / 21595 tokens
  39. 2.08.689.814 I slot print_timing: id 0 | task 0 | graphs reused = 11
  40. 2.08.689.816 I slot print_timing: id 0 | task 0 | draft acceptance = 0.42045 ( 74 accepted / 176 generated)
  41. 2.08.689.841 I statistics draft-mtp: #calls(b,g,a) = 1 11 11, #gen drafts = 11, #acc drafts = 9, #gen tokens = 176, #acc tokens = 74, dur(b,g,a) = 0.002, 535.616, 0.025 ms
  42. 2.08.691.088 I slot release: id 0 | task 0 | stop processing: n_tokens = 21596, truncated = 0
  43. 2.08.691.108 I srv update_slots: all slots are idle
  44. 2.09.007.056 I srv params_from_: Chat format: peg-native
  45. 2.09.043.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.905 (> 0.100 thold), f_keep = 1.000
  46. 2.09.044.403 I reasoning-budget: activated, budget=2147483647 tokens
  47. 2.09.044.588 I slot launch_slot_: id 0 | task 26 | processing task, is_child = 0
  48. 2.09.044.613 I slot update_slots: id 0 | task 26 | Checking checkpoint with [20647, 20647] against 21595...
  49. 2.09.109.817 W slot update_slots: id 0 | task 26 | restored context checkpoint (pos_min = 20647, pos_max = 20647, n_tokens = 20648, n_past = 20648, size = 192.869 MiB)
  50. 2.10.926.169 I slot create_check: id 0 | task 26 | created context checkpoint 2 of 32 (pos_min = 23336, pos_max = 23336, n_tokens = 23337, size = 198.500 MiB)
  51. 2.14.072.825 I slot print_timing: id 0 | task 26 | n_decoded = 103, tg = 39.24 t/s
  52. 2.17.189.140 I slot print_timing: id 0 | task 26 | n_decoded = 200, tg = 34.84 t/s
  53. 2.20.202.741 I slot print_timing: id 0 | task 26 | n_decoded = 258, tg = 29.47 t/s
  54. 2.23.259.022 I slot print_timing: id 0 | task 26 | n_decoded = 334, tg = 28.28 t/s
  55. 2.26.356.956 I slot print_timing: id 0 | task 26 | n_decoded = 407, tg = 27.30 t/s
  56. 2.27.490.553 I reasoning-budget: deactivated (natural end)
  57. 2.29.380.828 I slot print_timing: id 0 | task 26 | n_decoded = 557, tg = 31.06 t/s
  58. 2.29.671.311 I slot print_timing: id 0 | task 26 | prompt eval time = 2402.69 ms / 3205 tokens ( 0.75 ms per token, 1333.92 tokens per second)
  59. 2.29.671.316 I slot print_timing: id 0 | task 26 | eval time = 18222.43 ms / 582 tokens ( 31.31 ms per token, 31.94 tokens per second)
  60. 2.29.671.317 I slot print_timing: id 0 | task 26 | total time = 20625.12 ms / 3787 tokens
  61. 2.29.671.318 I slot print_timing: id 0 | task 26 | graphs reused = 181
  62. 2.29.671.319 I slot print_timing: id 0 | task 26 | draft acceptance = 0.14812 ( 410 accepted / 2768 generated)
  63. 2.29.671.339 I statistics draft-mtp: #calls(b,g,a) = 2 184 184, #gen drafts = 184, #acc drafts = 137, #gen tokens = 2944, #acc tokens = 484, dur(b,g,a) = 0.003, 8761.735, 0.391 ms
  64. 2.29.672.597 I slot release: id 0 | task 26 | stop processing: n_tokens = 24436, truncated = 0
  65. 2.29.672.788 I srv update_slots: all slots are idle
  66. 2.30.003.061 I srv params_from_: Chat format: peg-native
  67. 2.30.039.653 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.993 (> 0.100 thold), f_keep = 1.000
  68. 2.30.040.401 I reasoning-budget: activated, budget=2147483647 tokens
  69. 2.30.040.594 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0
  70. 2.30.040.644 I slot update_slots: id 0 | task 204 | Checking checkpoint with [23336, 23336] against 24435...
  71. 2.30.106.772 W slot update_slots: id 0 | task 204 | restored context checkpoint (pos_min = 23336, pos_max = 23336, n_tokens = 23337, n_past = 23337, size = 198.500 MiB)
  72. 2.31.088.345 I slot create_check: id 0 | task 204 | created context checkpoint 3 of 32 (pos_min = 24435, pos_max = 24435, n_tokens = 24436, size = 200.802 MiB)
  73. 2.32.103.938 I reasoning-budget: deactivated (natural end)
  74. 2.32.951.777 I slot print_timing: id 0 | task 204 | n_decoded = 103, tg = 64.05 t/s
  75. 2.34.433.170 I slot print_timing: id 0 | task 204 | prompt eval time = 1302.59 ms / 1267 tokens ( 1.03 ms per token, 972.68 tokens per second)
  76. 2.34.433.175 I slot print_timing: id 0 | task 204 | eval time = 3089.49 ms / 246 tokens ( 12.56 ms per token, 79.62 tokens per second)
  77. 2.34.433.176 I slot print_timing: id 0 | task 204 | total time = 4392.08 ms / 1513 tokens
  78. 2.34.433.177 I slot print_timing: id 0 | task 204 | graphs reused = 207
  79. 2.34.433.178 I slot print_timing: id 0 | task 204 | draft acceptance = 0.48884 ( 219 accepted / 448 generated)
  80. 2.34.433.196 I statistics draft-mtp: #calls(b,g,a) = 3 212 212, #gen drafts = 212, #acc drafts = 163, #gen tokens = 3392, #acc tokens = 703, dur(b,g,a) = 0.004, 10090.077, 0.456 ms
  81. 2.34.434.308 I slot release: id 0 | task 204 | stop processing: n_tokens = 24851, truncated = 0
  82. 2.34.434.438 I srv update_slots: all slots are idle
  83. 2.35.138.103 I srv params_from_: Chat format: peg-native
  84. 2.35.178.933 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.948 (> 0.100 thold), f_keep = 1.000
  85. 2.35.179.607 I reasoning-budget: activated, budget=2147483647 tokens
  86. 2.35.179.779 I slot launch_slot_: id 0 | task 237 | processing task, is_child = 0
  87. 2.35.179.804 I slot update_slots: id 0 | task 237 | Checking checkpoint with [24435, 24435] against 24850...
  88. 2.35.243.342 W slot update_slots: id 0 | task 237 | restored context checkpoint (pos_min = 24435, pos_max = 24435, n_tokens = 24436, n_past = 24436, size = 200.802 MiB)
  89. 2.36.347.385 I slot create_check: id 0 | task 237 | created context checkpoint 4 of 32 (pos_min = 25699, pos_max = 25699, n_tokens = 25700, size = 203.449 MiB)
  90. 2.38.174.256 I slot print_timing: id 0 | task 237 | n_decoded = 100, tg = 76.62 t/s
  91. 2.41.235.890 I slot print_timing: id 0 | task 237 | n_decoded = 257, tg = 58.86 t/s
  92. 2.43.304.252 I reasoning-budget: deactivated (natural end)
  93. 2.44.249.764 I slot print_timing: id 0 | task 237 | n_decoded = 367, tg = 49.73 t/s
  94. 2.47.250.189 I slot print_timing: id 0 | task 237 | n_decoded = 561, tg = 54.04 t/s
  95. 2.47.666.683 I slot print_timing: id 0 | task 237 | prompt eval time = 1688.92 ms / 1780 tokens ( 0.95 ms per token, 1053.93 tokens per second)
  96. 2.47.666.688 I slot print_timing: id 0 | task 237 | eval time = 10797.03 ms / 604 tokens ( 17.88 ms per token, 55.94 tokens per second)
  97. 2.47.666.690 I slot print_timing: id 0 | task 237 | total time = 12485.96 ms / 2384 tokens
  98. 2.47.666.691 I slot print_timing: id 0 | task 237 | graphs reused = 305
  99. 2.47.666.692 I slot print_timing: id 0 | task 237 | draft acceptance = 0.31188 ( 504 accepted / 1616 generated)
  100. 2.47.666.711 I statistics draft-mtp: #calls(b,g,a) = 4 313 313, #gen drafts = 313, #acc drafts = 256, #gen tokens = 5008, #acc tokens = 1207, dur(b,g,a) = 0.005, 14897.410, 0.675 ms
  101. 2.47.668.188 I slot release: id 0 | task 237 | stop processing: n_tokens = 26821, truncated = 0
  102. 2.47.668.332 I srv update_slots: all slots are idle
  103. 2.48.009.128 I srv params_from_: Chat format: peg-native
  104. 2.48.051.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.994 (> 0.100 thold), f_keep = 1.000
  105. 2.48.052.569 I reasoning-budget: activated, budget=2147483647 tokens
  106. 2.48.052.731 I slot launch_slot_: id 0 | task 343 | processing task, is_child = 0
  107. 2.48.052.752 I slot update_slots: id 0 | task 343 | Checking checkpoint with [25699, 25699] against 26820...
  108. 2.48.117.416 W slot update_slots: id 0 | task 343 | restored context checkpoint (pos_min = 25699, pos_max = 25699, n_tokens = 25700, n_past = 25700, size = 203.449 MiB)
  109. 2.49.135.513 I slot create_check: id 0 | task 343 | created context checkpoint 5 of 32 (pos_min = 26820, pos_max = 26820, n_tokens = 26821, size = 205.797 MiB)
  110. 2.52.331.611 I slot print_timing: id 0 | task 343 | n_decoded = 100, tg = 34.08 t/s
  111. 2.55.399.042 I slot print_timing: id 0 | task 343 | n_decoded = 211, tg = 35.16 t/s
  112. 2.55.503.824 I reasoning-budget: deactivated (natural end)
  113. 2.58.408.406 I slot print_timing: id 0 | task 343 | n_decoded = 410, tg = 45.50 t/s
  114. 3.01.421.726 I slot print_timing: id 0 | task 343 | n_decoded = 610, tg = 50.73 t/s
  115. 3.04.457.925 I slot print_timing: id 0 | task 343 | n_decoded = 812, tg = 53.92 t/s
  116. 3.07.517.081 I slot print_timing: id 0 | task 343 | n_decoded = 874, tg = 48.24 t/s
  117. 3.10.535.335 I slot print_timing: id 0 | task 343 | n_decoded = 1152, tg = 54.50 t/s
  118. 3.13.599.205 I slot print_timing: id 0 | task 343 | n_decoded = 1451, tg = 59.96 t/s
  119. 3.16.671.614 I slot print_timing: id 0 | task 343 | n_decoded = 1742, tg = 63.87 t/s
  120. 3.19.763.065 I slot print_timing: id 0 | task 343 | n_decoded = 2037, tg = 67.09 t/s
  121. 3.20.696.896 I slot print_timing: id 0 | task 343 | prompt eval time = 1344.41 ms / 1289 tokens ( 1.04 ms per token, 958.78 tokens per second)
  122. 3.20.696.902 I slot print_timing: id 0 | task 343 | eval time = 31297.66 ms / 2110 tokens ( 14.83 ms per token, 67.42 tokens per second)
  123. 3.20.696.903 I slot print_timing: id 0 | task 343 | total time = 32642.07 ms / 3399 tokens
  124. 3.20.696.904 I slot print_timing: id 0 | task 343 | graphs reused = 581
  125. 3.20.696.906 I slot print_timing: id 0 | task 343 | draft acceptance = 0.40044 ( 1826 accepted / 4560 generated)
  126. 3.20.696.929 I statistics draft-mtp: #calls(b,g,a) = 5 598 598, #gen drafts = 598, #acc drafts = 500, #gen tokens = 9568, #acc tokens = 3033, dur(b,g,a) = 0.006, 28785.682, 1.387 ms
  127. 3.20.698.079 I slot release: id 0 | task 343 | stop processing: n_tokens = 29100, truncated = 0
  128. 3.20.698.246 I srv update_slots: all slots are idle
  129. 3.21.209.579 I srv params_from_: Chat format: peg-native
  130. 3.21.254.470 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.935 (> 0.100 thold), f_keep = 0.936
  131. 3.21.255.203 I reasoning-budget: activated, budget=2147483647 tokens
  132. 3.21.255.377 I slot launch_slot_: id 0 | task 633 | processing task, is_child = 0
  133. 3.21.255.406 I slot update_slots: id 0 | task 633 | Checking checkpoint with [26820, 26820] against 27237...
  134. 3.21.322.972 W slot update_slots: id 0 | task 633 | restored context checkpoint (pos_min = 26820, pos_max = 26820, n_tokens = 26821, n_past = 26821, size = 205.797 MiB)
  135. 3.23.045.044 I slot create_check: id 0 | task 633 | created context checkpoint 6 of 32 (pos_min = 29098, pos_max = 29098, n_tokens = 29099, size = 210.567 MiB)
  136. 3.26.565.407 I slot print_timing: id 0 | task 633 | n_decoded = 100, tg = 29.89 t/s
  137. 3.29.604.663 I slot print_timing: id 0 | task 633 | n_decoded = 173, tg = 27.10 t/s
  138. 3.30.027.775 I reasoning-budget: deactivated (natural end)
  139. 3.32.640.037 I slot print_timing: id 0 | task 633 | n_decoded = 489, tg = 51.91 t/s
  140. 3.35.729.318 I slot print_timing: id 0 | task 633 | n_decoded = 866, tg = 69.23 t/s
  141. 3.38.760.901 I slot print_timing: id 0 | task 633 | n_decoded = 1193, tg = 76.77 t/s
  142. 3.41.770.202 I slot print_timing: id 0 | task 633 | n_decoded = 1578, tg = 85.07 t/s
  143. 3.44.809.220 I slot print_timing: id 0 | task 633 | n_decoded = 1968, tg = 91.16 t/s
  144. 3.46.593.156 I slot print_timing: id 0 | task 633 | prompt eval time = 1964.39 ms / 2323 tokens ( 0.85 ms per token, 1182.56 tokens per second)
  145. 3.46.593.163 I slot print_timing: id 0 | task 633 | eval time = 23371.68 ms / 2164 tokens ( 10.80 ms per token, 92.59 tokens per second)
  146. 3.46.593.165 I slot print_timing: id 0 | task 633 | total time = 25336.07 ms / 4487 tokens
  147. 3.46.593.166 I slot print_timing: id 0 | task 633 | graphs reused = 777
  148. 3.46.593.168 I slot print_timing: id 0 | task 633 | draft acceptance = 0.59436 ( 1959 accepted / 3296 generated)
  149. 3.46.593.190 I statistics draft-mtp: #calls(b,g,a) = 6 804 804, #gen drafts = 804, #acc drafts = 684, #gen tokens = 12864, #acc tokens = 4992, dur(b,g,a) = 0.007, 38902.456, 1.889 ms
  150. 3.46.595.009 I slot release: id 0 | task 633 | stop processing: n_tokens = 31309, truncated = 0
  151. 3.46.595.260 I srv update_slots: all slots are idle
  152. 3.47.076.133 I srv params_from_: Chat format: peg-native
  153. 3.47.120.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.936 (> 0.100 thold), f_keep = 0.938
  154. 3.47.120.960 I reasoning-budget: activated, budget=2147483647 tokens
  155. 3.47.121.159 I slot launch_slot_: id 0 | task 844 | processing task, is_child = 0
  156. 3.47.121.189 I slot update_slots: id 0 | task 844 | Checking checkpoint with [29098, 29098] against 29358...
  157. 3.47.189.424 W slot update_slots: id 0 | task 844 | restored context checkpoint (pos_min = 29098, pos_max = 29098, n_tokens = 29099, n_past = 29099, size = 210.567 MiB)
  158. 3.48.914.792 I slot create_check: id 0 | task 844 | created context checkpoint 7 of 32 (pos_min = 31307, pos_max = 31307, n_tokens = 31308, size = 215.194 MiB)
  159. 3.49.982.025 I reasoning-budget: deactivated (natural end)
  160. 3.50.647.926 I slot print_timing: id 0 | task 844 | n_decoded = 105, tg = 67.25 t/s
  161. 3.51.199.951 I slot print_timing: id 0 | task 844 | prompt eval time = 1964.88 ms / 2252 tokens ( 0.87 ms per token, 1146.12 tokens per second)
  162. 3.51.199.960 I slot print_timing: id 0 | task 844 | eval time = 2113.43 ms / 149 tokens ( 14.18 ms per token, 70.50 tokens per second)
  163. 3.51.199.961 I slot print_timing: id 0 | task 844 | total time = 4078.31 ms / 2401 tokens
  164. 3.51.199.962 I slot print_timing: id 0 | task 844 | graphs reused = 793
  165. 3.51.199.964 I slot print_timing: id 0 | task 844 | draft acceptance = 0.45833 ( 132 accepted / 288 generated)
  166. 3.51.199.987 I statistics draft-mtp: #calls(b,g,a) = 7 822 822, #gen drafts = 822, #acc drafts = 701, #gen tokens = 13152, #acc tokens = 5124, dur(b,g,a) = 0.008, 39793.233, 1.932 ms
  167. 3.51.201.309 I slot release: id 0 | task 844 | stop processing: n_tokens = 31501, truncated = 0
  168. 3.51.201.508 I srv update_slots: all slots are idle
  169. 3.51.545.116 I srv params_from_: Chat format: peg-native
  170. 3.51.589.166 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.995 (> 0.100 thold), f_keep = 1.000
  171. 3.51.590.056 I reasoning-budget: activated, budget=2147483647 tokens
  172. 3.51.590.317 I slot launch_slot_: id 0 | task 867 | processing task, is_child = 0
  173. 3.51.590.372 I slot update_slots: id 0 | task 867 | Checking checkpoint with [31307, 31307] against 31500...
  174. 3.51.665.298 W slot update_slots: id 0 | task 867 | restored context checkpoint (pos_min = 31307, pos_max = 31307, n_tokens = 31308, n_past = 31308, size = 215.194 MiB)
  175. 3.53.143.113 I reasoning-budget: deactivated (natural end)
  176. 3.53.974.726 I slot print_timing: id 0 | task 867 | n_decoded = 104, tg = 57.09 t/s
  177. 3.57.048.405 I slot print_timing: id 0 | task 867 | n_decoded = 440, tg = 89.88 t/s
  178. 4.00.049.271 I slot print_timing: id 0 | task 867 | n_decoded = 760, tg = 96.25 t/s
  179. 4.01.140.893 I slot print_timing: id 0 | task 867 | prompt eval time = 562.25 ms / 361 tokens ( 1.56 ms per token, 642.07 tokens per second)
  180. 4.01.140.910 I slot print_timing: id 0 | task 867 | eval time = 8987.45 ms / 862 tokens ( 10.43 ms per token, 95.91 tokens per second)
  181. 4.01.140.912 I slot print_timing: id 0 | task 867 | total time = 9549.70 ms / 1223 tokens
  182. 4.01.140.913 I slot print_timing: id 0 | task 867 | graphs reused = 868
  183. 4.01.140.915 I slot print_timing: id 0 | task 867 | draft acceptance = 0.61172 ( 783 accepted / 1280 generated)
  184. 4.01.140.941 I statistics draft-mtp: #calls(b,g,a) = 8 902 902, #gen drafts = 902, #acc drafts = 779, #gen tokens = 14432, #acc tokens = 5907, dur(b,g,a) = 0.009, 43616.960, 2.120 ms
  185. 4.01.142.517 I slot release: id 0 | task 867 | stop processing: n_tokens = 32532, truncated = 0
  186. 4.01.142.805 I srv update_slots: all slots are idle
  187. 4.02.014.930 I srv params_from_: Chat format: peg-native
  188. 4.02.064.879 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.974 (> 0.100 thold), f_keep = 0.975
  189. 4.02.065.533 I reasoning-budget: activated, budget=2147483647 tokens
  190. 4.02.065.702 I slot launch_slot_: id 0 | task 951 | processing task, is_child = 0
  191. 4.02.065.732 I slot update_slots: id 0 | task 951 | Checking checkpoint with [31307, 31307] against 31717...
  192. 4.02.140.842 W slot update_slots: id 0 | task 951 | restored context checkpoint (pos_min = 31307, pos_max = 31307, n_tokens = 31308, n_past = 31308, size = 215.194 MiB)
  193. 4.03.294.418 I slot create_check: id 0 | task 951 | created context checkpoint 8 of 32 (pos_min = 32530, pos_max = 32530, n_tokens = 32531, size = 217.755 MiB)
  194. 4.03.839.666 I reasoning-budget: deactivated (natural end)
  195. 4.04.877.005 I slot print_timing: id 0 | task 951 | prompt eval time = 1397.39 ms / 1263 tokens ( 1.11 ms per token, 903.83 tokens per second)
  196. 4.04.877.011 I slot print_timing: id 0 | task 951 | eval time = 1413.48 ms / 100 tokens ( 14.13 ms per token, 70.75 tokens per second)
  197. 4.04.877.012 I slot print_timing: id 0 | task 951 | total time = 2810.86 ms / 1363 tokens
  198. 4.04.877.013 I slot print_timing: id 0 | task 951 | graphs reused = 878
  199. 4.04.877.015 I slot print_timing: id 0 | task 951 | draft acceptance = 0.51136 ( 90 accepted / 176 generated)
  200. 4.04.877.035 I statistics draft-mtp: #calls(b,g,a) = 9 913 913, #gen drafts = 913, #acc drafts = 790, #gen tokens = 14608, #acc tokens = 5997, dur(b,g,a) = 0.011, 44185.714, 2.152 ms
  201. 4.04.878.783 I slot release: id 0 | task 951 | stop processing: n_tokens = 32672, truncated = 0
  202. 4.04.879.031 I slot print_timing: id 0 | task -1 | n_decoded = 100, tg = 70.64 t/s
  203. 4.04.879.040 I srv update_slots: all slots are idle
  204. 4.09.462.178 I srv params_from_: Chat format: peg-native
  205. 4.09.512.949 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.998 (> 0.100 thold), f_keep = 1.000
  206. 4.09.513.615 I reasoning-budget: activated, budget=2147483647 tokens
  207. 4.09.513.848 I slot launch_slot_: id 0 | task 967 | processing task, is_child = 0
  208. 4.09.513.905 I slot update_slots: id 0 | task 967 | Checking checkpoint with [32530, 32530] against 32671...
  209. 4.09.584.140 W slot update_slots: id 0 | task 967 | restored context checkpoint (pos_min = 32530, pos_max = 32530, n_tokens = 32531, n_past = 32531, size = 217.755 MiB)
  210. 4.10.069.159 I slot print_timing: id 0 | task 967 | prompt eval time = 555.24 ms / 207 tokens ( 2.68 ms per token, 372.82 tokens per second)
  211. 4.10.069.168 I slot print_timing: id 0 | task 967 | eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, 1000000.00 tokens per second)
  212. 4.10.069.169 I slot print_timing: id 0 | task 967 | total time = 555.24 ms / 208 tokens
  213. 4.10.069.172 I slot print_timing: id 0 | task 967 | graphs reused = 878
  214. 4.10.069.193 I statistics draft-mtp: #calls(b,g,a) = 10 913 913, #gen drafts = 913, #acc drafts = 790, #gen tokens = 14608, #acc tokens = 5997, dur(b,g,a) = 0.013, 44185.714, 2.152 ms
  215. 4.10.070.707 I slot release: id 0 | task 967 | stop processing: n_tokens = 32738, truncated = 0
  216. 4.10.070.902 I srv update_slots: all slots are idle
  217. 4.12.303.479 I srv params_from_: Chat format: peg-native
  218. 4.12.348.776 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
  219. 4.12.349.448 I reasoning-budget: activated, budget=2147483647 tokens
  220. 4.12.350.176 I slot launch_slot_: id 0 | task 971 | processing task, is_child = 0
  221. 4.12.350.216 I slot update_slots: id 0 | task 971 | Checking checkpoint with [32530, 32530] against 32737...
  222. 4.12.420.964 W slot update_slots: id 0 | task 971 | restored context checkpoint (pos_min = 32530, pos_max = 32530, n_tokens = 32531, n_past = 32531, size = 217.755 MiB)
  223. 4.12.884.533 I reasoning-budget: deactivated (natural end)
  224. 4.13.842.451 I slot print_timing: id 0 | task 971 | n_decoded = 115, tg = 120.09 t/s
  225. 4.14.023.696 I slot print_timing: id 0 | task 971 | prompt eval time = 534.32 ms / 207 tokens ( 2.58 ms per token, 387.41 tokens per second)
  226. 4.14.023.702 I slot print_timing: id 0 | task 971 | eval time = 1138.86 ms / 127 tokens ( 8.97 ms per token, 111.51 tokens per second)
  227. 4.14.023.704 I slot print_timing: id 0 | task 971 | total time = 1673.18 ms / 334 tokens
  228. 4.14.023.704 I slot print_timing: id 0 | task 971 | graphs reused = 885
  229. 4.14.023.706 I slot print_timing: id 0 | task 971 | draft acceptance = 0.82639 ( 119 accepted / 144 generated)
  230. 4.14.023.726 I statistics draft-mtp: #calls(b,g,a) = 11 922 922, #gen drafts = 922, #acc drafts = 799, #gen tokens = 14752, #acc tokens = 6116, dur(b,g,a) = 0.014, 44626.681, 2.173 ms
  231. 4.14.025.395 I slot release: id 0 | task 971 | stop processing: n_tokens = 32866, truncated = 0
  232. 4.14.025.644 I srv update_slots: all slots are idle
  233. 4.14.356.203 I srv params_from_: Chat format: peg-native
  234. 4.14.402.387 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, sim_best = 0.991 (> 0.100 thold), f_keep = 0.996
  235. 4.14.403.042 I reasoning-budget: activated, budget=2147483647 tokens
  236. 4.14.403.265 I slot launch_slot_: id 0 | task 984 | processing task, is_child = 0
  237. 4.14.403.292 I slot update_slots: id 0 | task 984 | Checking checkpoint with [32530, 32530] against 32736...
  238. 4.14.474.415 W slot update_slots: id 0 | task 984 | restored context checkpoint (pos_min = 32530, pos_max = 32530, n_tokens = 32531, n_past = 32531, size = 217.755 MiB)
  239. 4.15.842.044 I reasoning-budget: deactivated (natural end)
  240. 4.18.107.314 I slot print_timing: id 0 | task 984 | n_decoded = 101, tg = 33.13 t/s
  241. 4.21.129.190 I slot print_timing: id 0 | task 984 | n_decoded = 222, tg = 36.57 t/s
  242. 4.23.102.878 I slot print_timing: id 0 | task 984 | prompt eval time = 654.77 ms / 502 tokens ( 1.30 ms per token, 766.69 tokens per second)
  243. 4.23.102.887 I slot print_timing: id 0 | task 984 | eval time = 8044.07 ms / 311 tokens ( 25.87 ms per token, 38.66 tokens per second)
  244. 4.23.102.888 I slot print_timing: id 0 | task 984 | total time = 8698.84 ms / 813 tokens
  245. 4.23.102.889 I slot print_timing: id 0 | task 984 | graphs reused = 957
  246. 4.23.102.891 I slot print_timing: id 0 | task 984 | draft acceptance = 0.20270 ( 240 accepted / 1184 generated)
  247. 4.23.102.910 I statistics draft-mtp: #calls(b,g,a) = 12 996 996, #gen drafts = 996, #acc drafts = 863, #gen tokens = 15936, #acc tokens = 6356, dur(b,g,a) = 0.015, 48217.374, 2.316 ms
  248. 4.23.105.046 I slot release: id 0 | task 984 | stop processing: n_tokens = 33347, truncated = 0
  249. 4.23.105.230 I srv update_slots: all slots are idle
  250. 9.38.908.740 I srv operator(): operator(): cleaning up before exit...
  251.  
  252. total : 2.29s
  253.  
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!