Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- fauxpilot-copilot_proxy-1 | Returned completion in 82816.30563735962 ms 1679737428.549292
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:43:48,549 :: 74.235.184.25:47144 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 82816.67017936707 ms 1679737428.5498981
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:43:48,550 :: 74.235.184.25:47152 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 82816.81108474731 ms 1679737428.5502555
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:43:48,550 :: 74.235.184.25:47158 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 82816.92790985107 ms 1679737428.5505447
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:43:48,550 :: 74.235.184.25:47164 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 82817.0337677002 ms 1679737428.55082
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:43:48,550 :: 74.235.184.25:47172 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 82817.1739578247 ms 1679737428.5511227
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:43:48,551 :: 74.235.184.25:47180 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | got request 1679737428.552212
- fauxpilot-triton-1 | W0325 09:43:49.554066 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:43:49.554241 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:43:49.554345 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:43:49.554452 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:43:49.554566 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554615 89 libfastertransformer.cc:1117] collect name: input_ids size: 540 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554641 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554667 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554694 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554720 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554746 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554772 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554799 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554825 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554851 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554877 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554903 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554929 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554956 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.554982 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:43:49.555007 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:43:49.555032 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:43:49.555203 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:43:49.555361 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:43:49.555550 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:44:06.115290 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:44:06.115451 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:44:06.115483 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:44:06.115552 89 libfastertransformer.cc:1191] output shape: [1, 1, 635]
- fauxpilot-triton-1 | W0325 09:44:06.115640 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:44:06.115690 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:44:06.115747 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:44:06.115815 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:44:06.115880 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-triton-1 | W0325 09:44:06.116036 89 libfastertransformer.cc:795] response is sent
- fauxpilot-copilot_proxy-1 | Returned completion in 17564.770460128784 ms 1679737446.1169825
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:44:06,117 :: 74.235.184.25:45654 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | got request 1679737446.1195467
- fauxpilot-copilot_proxy-1 | got request 1679737446.1197827
- fauxpilot-copilot_proxy-1 | got request 1679737446.1199694
- fauxpilot-copilot_proxy-1 | got request 1679737446.120142
- fauxpilot-copilot_proxy-1 | got request 1679737446.1203208
- fauxpilot-copilot_proxy-1 | got request 1679737446.1205049
- fauxpilot-triton-1 | W0325 09:44:07.123815 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:44:07.123867 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:44:07.123880 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:44:07.123895 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:44:07.123916 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.123938 89 libfastertransformer.cc:1117] collect name: input_ids size: 2696 bytes
- fauxpilot-triton-1 | W0325 09:44:07.123951 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:44:07.123963 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.123977 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.123990 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124003 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124018 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124031 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124043 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124055 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124067 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124079 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124090 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124104 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124116 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:07.124128 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:44:07.124138 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:44:07.124160 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:44:07.124253 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:44:07.124435 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:44:26.125114 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:44:26.125305 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:44:26.125327 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:44:26.125331 89 libfastertransformer.cc:1191] output shape: [1, 1, 1174]
- fauxpilot-triton-1 | W0325 09:44:26.125363 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:44:26.125367 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:44:26.125370 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:44:26.125385 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:44:26.125393 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-triton-1 | W0325 09:44:26.125518 89 libfastertransformer.cc:795] response is sent
- fauxpilot-triton-1 | W0325 09:44:27.131119 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:44:27.131176 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:44:27.131188 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:44:27.131202 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:44:27.131224 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131247 89 libfastertransformer.cc:1117] collect name: input_ids size: 5444 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131262 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131273 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131287 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131301 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131314 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131328 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131342 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131355 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131368 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131380 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131391 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131403 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131418 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131439 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:27.131452 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:44:27.131463 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:44:27.131485 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:44:27.131530 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:44:27.131633 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:44:49.196372 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:44:49.196562 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:44:49.196581 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:44:49.196586 89 libfastertransformer.cc:1191] output shape: [1, 1, 1861]
- fauxpilot-triton-1 | W0325 09:44:49.196621 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:44:49.196626 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:44:49.196629 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:44:49.196644 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:44:49.196654 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-triton-1 | W0325 09:44:49.196781 89 libfastertransformer.cc:795] response is sent
- fauxpilot-triton-1 | W0325 09:44:50.200287 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:44:50.200342 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:44:50.200355 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:44:50.200369 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:44:50.200390 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200411 89 libfastertransformer.cc:1117] collect name: input_ids size: 2392 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200424 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200435 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200449 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200462 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200475 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200491 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200503 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200515 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200528 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200541 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200554 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200567 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200581 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200595 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:44:50.200608 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:44:50.200619 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:44:50.200641 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:44:50.200745 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:44:50.200833 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:45:08.857338 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:45:08.857530 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:45:08.857547 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:45:08.857552 89 libfastertransformer.cc:1191] output shape: [1, 1, 1098]
- fauxpilot-triton-1 | W0325 09:45:08.857583 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:45:08.857586 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:45:08.857589 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:45:08.857603 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:45:08.857608 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-triton-1 | W0325 09:45:08.857706 89 libfastertransformer.cc:795] response is sent
- fauxpilot-triton-1 | W0325 09:45:09.860855 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:45:09.860905 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:45:09.860918 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:45:09.860933 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:45:09.860955 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.860977 89 libfastertransformer.cc:1117] collect name: input_ids size: 1624 bytes
- fauxpilot-triton-1 | W0325 09:45:09.860991 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861002 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861015 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861028 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861041 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861054 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861067 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861079 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861092 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861104 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861117 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861130 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861145 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861158 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:09.861171 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:45:09.861182 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:45:09.861205 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:45:09.861351 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:45:09.861442 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:45:27.665372 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:45:27.665556 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:45:27.665575 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:45:27.665579 89 libfastertransformer.cc:1191] output shape: [1, 1, 906]
- fauxpilot-triton-1 | W0325 09:45:27.665610 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:45:27.665617 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:45:27.665620 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:45:27.665634 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:45:27.665645 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-triton-1 | W0325 09:45:27.665752 89 libfastertransformer.cc:795] response is sent
- fauxpilot-triton-1 | W0325 09:45:28.671867 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:45:28.671924 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:45:28.671937 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:45:28.671955 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:45:28.671977 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672000 89 libfastertransformer.cc:1117] collect name: input_ids size: 6400 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672013 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672024 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672038 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672052 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672066 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672078 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672091 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672103 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672116 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672128 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672140 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672152 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672168 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672196 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:28.672208 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:45:28.672217 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:45:28.672240 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:45:28.672282 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:45:28.672449 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:45:49.029485 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:45:49.029714 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:45:49.029734 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:45:49.029739 89 libfastertransformer.cc:1191] output shape: [1, 1, 2042]
- fauxpilot-triton-1 | W0325 09:45:49.029789 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:45:49.029798 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:45:49.029801 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:45:49.029817 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:45:49.029826 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-triton-1 | W0325 09:45:49.029977 89 libfastertransformer.cc:795] response is sent
- fauxpilot-triton-1 | W0325 09:45:50.035721 89 libfastertransformer.cc:1397] model fastertransformer, instance fastertransformer_0, executing 1 requests
- fauxpilot-triton-1 | W0325 09:45:50.035771 89 libfastertransformer.cc:638] TRITONBACKEND_ModelExecute: Running fastertransformer_0 with 1 requests
- fauxpilot-triton-1 | W0325 09:45:50.035784 89 libfastertransformer.cc:693] get total batch_size = 1
- fauxpilot-triton-1 | W0325 09:45:50.035803 89 libfastertransformer.cc:1051] get input count = 16
- fauxpilot-triton-1 | W0325 09:45:50.035826 89 libfastertransformer.cc:1117] collect name: start_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035851 89 libfastertransformer.cc:1117] collect name: input_ids size: 5508 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035863 89 libfastertransformer.cc:1117] collect name: bad_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035875 89 libfastertransformer.cc:1117] collect name: random_seed size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035889 89 libfastertransformer.cc:1117] collect name: end_id size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035901 89 libfastertransformer.cc:1117] collect name: input_lengths size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035916 89 libfastertransformer.cc:1117] collect name: request_output_len size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035929 89 libfastertransformer.cc:1117] collect name: runtime_top_k size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035943 89 libfastertransformer.cc:1117] collect name: runtime_top_p size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035956 89 libfastertransformer.cc:1117] collect name: is_return_log_probs size: 1 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035970 89 libfastertransformer.cc:1117] collect name: stop_words_list size: 8 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035983 89 libfastertransformer.cc:1117] collect name: temperature size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.035996 89 libfastertransformer.cc:1117] collect name: len_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.036008 89 libfastertransformer.cc:1117] collect name: beam_width size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.036024 89 libfastertransformer.cc:1117] collect name: beam_search_diversity_rate size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.036036 89 libfastertransformer.cc:1117] collect name: repetition_penalty size: 4 bytes
- fauxpilot-triton-1 | W0325 09:45:50.036048 89 libfastertransformer.cc:1130] the data is in CPU
- fauxpilot-triton-1 | W0325 09:45:50.036058 89 libfastertransformer.cc:1137] the data is in CPU
- fauxpilot-triton-1 | W0325 09:45:50.036080 89 libfastertransformer.cc:999] before ThreadForward 0
- fauxpilot-triton-1 | W0325 09:45:50.036197 89 libfastertransformer.cc:1006] after ThreadForward 0
- fauxpilot-triton-1 | I0325 09:45:50.036365 89 libfastertransformer.cc:834] Start to forward
- fauxpilot-triton-1 | I0325 09:46:12.174991 89 libfastertransformer.cc:836] Stop to forward
- fauxpilot-triton-1 | W0325 09:46:12.175057 89 libfastertransformer.cc:1161] Get output_tensors 0: output_ids
- fauxpilot-triton-1 | W0325 09:46:12.175063 89 libfastertransformer.cc:1171] output_type: UINT32
- fauxpilot-triton-1 | W0325 09:46:12.175068 89 libfastertransformer.cc:1191] output shape: [1, 1, 1877]
- fauxpilot-triton-1 | W0325 09:46:12.175094 89 libfastertransformer.cc:1161] Get output_tensors 1: sequence_length
- fauxpilot-triton-1 | W0325 09:46:12.175101 89 libfastertransformer.cc:1171] output_type: INT32
- fauxpilot-triton-1 | W0325 09:46:12.175104 89 libfastertransformer.cc:1191] output shape: [1, 1]
- fauxpilot-triton-1 | W0325 09:46:12.175118 89 libfastertransformer.cc:1206] PERFORMED GPU copy: NO
- fauxpilot-triton-1 | W0325 09:46:12.175127 89 libfastertransformer.cc:780] get response size = 1
- fauxpilot-copilot_proxy-1 | Returned completion in 126056.41746520996 ms 1679737572.175964
- fauxpilot-triton-1 | W0325 09:46:12.175842 89 libfastertransformer.cc:795] response is sent
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:46:12,176 :: 74.235.184.25:58080 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 126056.7717552185 ms 1679737572.1765544
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:46:12,176 :: 74.235.184.25:58092 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 126056.95390701294 ms 1679737572.1769233
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:46:12,177 :: 74.235.184.25:58096 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 126057.10625648499 ms 1679737572.1772482
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:46:12,177 :: 74.235.184.25:58100 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 126057.24573135376 ms 1679737572.1775665
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:46:12,177 :: 74.235.184.25:58104 - "POST /v1/completions HTTP/1.1" 200 OK
- fauxpilot-copilot_proxy-1 | Returned completion in 126057.34062194824 ms 1679737572.1778455
- fauxpilot-copilot_proxy-1 | INFO: 2023-03-25 09:46:12,177 :: 74.235.184.25:58114 - "POST /v1/completions HTTP/1.1" 200 OK
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement