40 lines
19 KiB
JSON
40 lines
19 KiB
JSON
{"label": "eager", "time": 1789663943.2948034, "event": "REQUEST_START", "name": "warmup", "profile": false, "prompt_tokens_preflight": 51}
|
|
{"label": "eager", "time": 1789663945.101216, "event": "RESULT", "name": "warmup", "profile": false, "correct": true, "content": "\n\n323", "finish_reason": "stop", "usage": {"prompt_tokens": 51, "total_tokens": 83, "completion_tokens": 32, "completion_tokens_details": {"reasoning_tokens": 26}}, "max_tokens": 2048, "prompt_sha256": "4181e1a44a0bed10d00c74e822377bd75a6c6c9a1ea458f5170b8193e9fce959", "output_sha256": "4477e82dcd9f3f8da1dd56be073d72e4ba20121d6ce6fbc97ee54258fb4b2959", "ttft_s": 0.8800418169994373, "first_content_s": 1.7162362779999967, "elapsed_s": 1.800662048997765, "decode_tps_approx": 37.07271627093361, "metrics_delta": {"vllm:prefix_cache_queries_total": 51.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789663945.1120813, "event": "REQUEST_START", "name": "short-0", "profile": false, "prompt_tokens_preflight": 65}
|
|
{"label": "eager", "time": 1789663952.799862, "event": "RESULT", "name": "short-0", "profile": false, "correct": true, "content": "\n\n数据库索引类似于书籍的目录，它通过B+树等数据结构将数据按特定字段有序组织，使查询时能快速定位目标记录，避免全表扫描，从而大幅提升读取效率。然而，索引对写入操作有负面影响：每次插入、更新或删除数据时，数据库都需要同步维护索引结构，这会增加额外的I/O和计算开销，导致写入性能下降。因此，索引是\"以空间换时间\"的典型策略，需根据实际读写比例合理设计。", "finish_reason": "stop", "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "max_tokens": 512, "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "ttft_s": 0.33354272600263357, "first_content_s": 3.9721969300007913, "elapsed_s": 7.68168595500174, "decode_tps_approx": 28.987645227728436, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789663952.8174412, "event": "REQUEST_START", "name": "prefill-8192-0", "profile": false, "prompt_tokens_preflight": 8173}
|
|
{"label": "eager", "time": 1789663958.6588385, "event": "RESULT", "name": "prefill-8192-0", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8236, "completion_tokens": 63, "completion_tokens_details": {"reasoning_tokens": 55}}, "max_tokens": 2048, "prompt_sha256": "f59f163e1c7bb8a79d08df830d94d6d2e98fec457e9de75e3c09f6fca7ab0813", "output_sha256": "09d17d110b06ec13d532382c41ea29955b7edfa8dd4bd34163a08fa746e56610", "ttft_s": 4.006232126004761, "first_content_s": 5.657178637004108, "elapsed_s": 5.835497587999271, "decode_tps_approx": 35.584837627199924, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789663958.6799748, "event": "REQUEST_START", "name": "reuse-8192-0", "profile": false, "prompt_tokens_preflight": 8173}
|
|
{"label": "eager", "time": 1789663961.4358463, "event": "RESULT", "name": "reuse-8192-0", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8236, "completion_tokens": 63, "completion_tokens_details": {"reasoning_tokens": 55}}, "max_tokens": 2048, "prompt_sha256": "f59f163e1c7bb8a79d08df830d94d6d2e98fec457e9de75e3c09f6fca7ab0813", "output_sha256": "09d17d110b06ec13d532382c41ea29955b7edfa8dd4bd34163a08fa746e56610", "ttft_s": 0.8856951920024585, "first_content_s": 2.5918558570047026, "elapsed_s": 2.7496982970042154, "decode_tps_approx": 34.74998178667343, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 6400.0}}
|
|
{"label": "eager", "time": 1789663961.4779031, "event": "REQUEST_START", "name": "prefill-32768-0", "profile": false, "prompt_tokens_preflight": 32745}
|
|
{"label": "eager", "time": 1789663979.3212829, "event": "RESULT", "name": "prefill-32768-0", "profile": false, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32745, "total_tokens": 32819, "completion_tokens": 74, "completion_tokens_details": {"reasoning_tokens": 66}}, "max_tokens": 2048, "prompt_sha256": "605f7b492252f50eaf60e8d128dde3f2d2e1b50dd26f0b45db88dac00e36a5ca", "output_sha256": "997501e1996b1c37af707622b1c4caf8dba93113e868f28210bd47ba700b5804", "ttft_s": 15.595506220997777, "first_content_s": 17.658189941001183, "elapsed_s": 17.837196191001567, "decode_tps_approx": 33.795316059955795, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789663979.3644226, "event": "REQUEST_START", "name": "reuse-32768-0", "profile": false, "prompt_tokens_preflight": 32745}
|
|
{"label": "eager", "time": 1789663982.9494953, "event": "RESULT", "name": "reuse-32768-0", "profile": false, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32745, "total_tokens": 32815, "completion_tokens": 70, "completion_tokens_details": {"reasoning_tokens": 62}}, "max_tokens": 2048, "prompt_sha256": "605f7b492252f50eaf60e8d128dde3f2d2e1b50dd26f0b45db88dac00e36a5ca", "output_sha256": "7eec57291da7ee95ae6d9214f8ed940a405e64beb9f49a4693387362aac3e14c", "ttft_s": 1.368702627994935, "first_content_s": 3.42049944599421, "elapsed_s": 3.579059300995141, "decode_tps_approx": 32.419700549347965, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 30400.0}}
|
|
{"label": "eager", "time": 1789663982.957122, "event": "REQUEST_START", "name": "short-1", "profile": false, "prompt_tokens_preflight": 65}
|
|
{"label": "eager", "time": 1789663990.3364515, "event": "RESULT", "name": "short-1", "profile": false, "correct": true, "content": "\n\n数据库索引类似于书籍的目录，它通过B+树等数据结构将数据按特定字段有序组织，使查询时能快速定位目标记录，避免全表扫描，从而大幅提升读取效率。然而，索引对写入操作有负面影响：每次插入、更新或删除数据时，数据库都需要同步维护索引结构，这会增加额外的I/O和计算开销，导致写入性能下降。因此，索引是\"以空间换时间\"的典型策略，需根据实际读写比例合理设计。", "finish_reason": "stop", "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "max_tokens": 512, "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "ttft_s": 0.2627224419993581, "first_content_s": 3.7929709769960027, "elapsed_s": 7.373869219998596, "decode_tps_approx": 29.953694756255302, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789663990.3527281, "event": "REQUEST_START", "name": "prefill-8192-1", "profile": false, "prompt_tokens_preflight": 8173}
|
|
{"label": "eager", "time": 1789663995.9852123, "event": "RESULT", "name": "prefill-8192-1", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8236, "completion_tokens": 63, "completion_tokens_details": {"reasoning_tokens": 55}}, "max_tokens": 2048, "prompt_sha256": "6c13deb2d4ddee54db95d7ebc8a1b87d24ed8a4112c33644c18b6b5d61ad7a16", "output_sha256": "09d17d110b06ec13d532382c41ea29955b7edfa8dd4bd34163a08fa746e56610", "ttft_s": 3.7754420729979756, "first_content_s": 5.466695101997175, "elapsed_s": 5.626387860997056, "decode_tps_approx": 35.041074313706375, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789663996.0020921, "event": "REQUEST_START", "name": "reuse-8192-1", "profile": false, "prompt_tokens_preflight": 8173}
|
|
{"label": "eager", "time": 1789663998.84421, "event": "RESULT", "name": "reuse-8192-1", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8242, "completion_tokens": 69, "completion_tokens_details": {"reasoning_tokens": 61}}, "max_tokens": 2048, "prompt_sha256": "6c13deb2d4ddee54db95d7ebc8a1b87d24ed8a4112c33644c18b6b5d61ad7a16", "output_sha256": "f72eba21a095aa0a43356b25cb120346b064d7f0a253a63cee7579d2c3422b82", "ttft_s": 0.8737719170021592, "first_content_s": 2.675332922997768, "elapsed_s": 2.835690722997242, "decode_tps_approx": 36.047200027797416, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 6400.0}}
|
|
{"label": "eager", "time": 1789663998.8886485, "event": "REQUEST_START", "name": "prefill-32768-1", "profile": false, "prompt_tokens_preflight": 32745}
|
|
{"label": "eager", "time": 1789664016.1901195, "event": "RESULT", "name": "prefill-32768-1", "profile": false, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32745, "total_tokens": 32812, "completion_tokens": 67, "completion_tokens_details": {"reasoning_tokens": 59}}, "max_tokens": 2048, "prompt_sha256": "0a5e4ba33ff264d180b8a56d89184c0fefad59a96fdd348d655bd54fe5b5ed45", "output_sha256": "ca2e8f89b165bee277a12cac7bb1cbc8ce34eef2ee29ecd1a8a46aa71c502cfa", "ttft_s": 15.403379977004079, "first_content_s": 17.130364165001083, "elapsed_s": 17.295454844999767, "decode_tps_approx": 36.438073002765556, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789664016.2312467, "event": "REQUEST_START", "name": "reuse-32768-1", "profile": false, "prompt_tokens_preflight": 32745}
|
|
{"label": "eager", "time": 1789664019.7841623, "event": "RESULT", "name": "reuse-32768-1", "profile": false, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32745, "total_tokens": 32815, "completion_tokens": 70, "completion_tokens_details": {"reasoning_tokens": 62}}, "max_tokens": 2048, "prompt_sha256": "0a5e4ba33ff264d180b8a56d89184c0fefad59a96fdd348d655bd54fe5b5ed45", "output_sha256": "7eec57291da7ee95ae6d9214f8ed940a405e64beb9f49a4693387362aac3e14c", "ttft_s": 1.367758443004277, "first_content_s": 3.3833834170000046, "elapsed_s": 3.5468969909998123, "decode_tps_approx": 32.877578996597116, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 30400.0}}
|
|
{"label": "eager", "time": 1789664019.7920012, "event": "REQUEST_START", "name": "short-2", "profile": false, "prompt_tokens_preflight": 65}
|
|
{"label": "eager", "time": 1789664027.1539514, "event": "RESULT", "name": "short-2", "profile": false, "correct": true, "content": "\n\n数据库索引类似于书籍的目录，它通过B+树等数据结构将数据按特定字段有序组织，使查询时能快速定位目标记录，避免全表扫描，从而大幅提升读取效率。然而，索引对写入操作有负面影响：每次插入、更新或删除数据时，数据库都需要同步维护索引结构，这会增加额外的I/O和计算开销，导致写入性能下降。因此，索引是\"以空间换时间\"的典型策略，需根据实际读写比例合理设计。", "finish_reason": "stop", "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "max_tokens": 512, "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "ttft_s": 0.26176839799882146, "first_content_s": 3.792491918997257, "elapsed_s": 7.35648784199293, "decode_tps_approx": 30.02293954286349, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789664027.17096, "event": "REQUEST_START", "name": "prefill-8192-2", "profile": false, "prompt_tokens_preflight": 8173}
|
|
{"label": "eager", "time": 1789664032.9165242, "event": "RESULT", "name": "prefill-8192-2", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8235, "completion_tokens": 62, "completion_tokens_details": {"reasoning_tokens": 54}}, "max_tokens": 2048, "prompt_sha256": "b49f6dbbf80f49ad860a60b0a7c58dfc2122e38bb8493ae155790f22305d8f7a", "output_sha256": "0eb9ce304c0547f0814d0590d36cb2144dcc242a2c550f3ba9f8a70b2e22b203", "ttft_s": 3.7875278329956927, "first_content_s": 5.574596539998311, "elapsed_s": 5.739436170995759, "decode_tps_approx": 32.64277985613848, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789664032.9353032, "event": "REQUEST_START", "name": "reuse-8192-2", "profile": false, "prompt_tokens_preflight": 8173}
|
|
{"label": "eager", "time": 1789664035.7520719, "event": "RESULT", "name": "reuse-8192-2", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8242, "completion_tokens": 69, "completion_tokens_details": {"reasoning_tokens": 61}}, "max_tokens": 2048, "prompt_sha256": "b49f6dbbf80f49ad860a60b0a7c58dfc2122e38bb8493ae155790f22305d8f7a", "output_sha256": "f72eba21a095aa0a43356b25cb120346b064d7f0a253a63cee7579d2c3422b82", "ttft_s": 0.8803304789980757, "first_content_s": 2.651041837001685, "elapsed_s": 2.811309409997193, "decode_tps_approx": 36.74879746387076, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 6400.0}}
|
|
{"label": "eager", "time": 1789664035.7953794, "event": "REQUEST_START", "name": "prefill-32768-2", "profile": false, "prompt_tokens_preflight": 32745}
|
|
{"label": "eager", "time": 1789664053.153125, "event": "RESULT", "name": "prefill-32768-2", "profile": false, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32745, "total_tokens": 32814, "completion_tokens": 69, "completion_tokens_details": {"reasoning_tokens": 61}}, "max_tokens": 2048, "prompt_sha256": "d8796cea8608150048ce4f253e451ba96da5416ccfea4a6560dc2f6bb2412004", "output_sha256": "8b503330d6b70b8845bab80540601fc48c8f840d54d07f38d80250c8167de89f", "ttft_s": 15.41581593700539, "first_content_s": 17.18937433300016, "elapsed_s": 17.35202403000585, "decode_tps_approx": 36.713832650404036, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789664053.1986973, "event": "REQUEST_START", "name": "reuse-32768-2", "profile": false, "prompt_tokens_preflight": 32745}
|
|
{"label": "eager", "time": 1789664056.5784104, "event": "RESULT", "name": "reuse-32768-2", "profile": false, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32745, "total_tokens": 32814, "completion_tokens": 69, "completion_tokens_details": {"reasoning_tokens": 61}}, "max_tokens": 2048, "prompt_sha256": "d8796cea8608150048ce4f253e451ba96da5416ccfea4a6560dc2f6bb2412004", "output_sha256": "8b503330d6b70b8845bab80540601fc48c8f840d54d07f38d80250c8167de89f", "ttft_s": 1.357998088002205, "first_content_s": 3.2952792900032364, "elapsed_s": 3.3747847780032316, "decode_tps_approx": 33.71865583479496, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 30400.0}}
|
|
{"label": "eager", "time": 1789664056.5835583, "event": "REQUEST_START", "name": "trace-short", "profile": true, "prompt_tokens_preflight": 65}
|
|
{"label": "eager", "time": 1789664067.1052518, "event": "RESULT", "name": "trace-short", "profile": true, "correct": true, "content": "\n\n数据库索引类似于书籍的目录，它通过B+树等数据结构将数据按特定字段有序组织，使查询时能快速定位目标记录，避免全表扫描，从而大幅提升读取效率。然而，索引对写入操作有负面影响：每次插入、更新或删除数据时，数据库都需要同步维护索引结构，这会增加额外的I/O和计算开销，导致写入性能下降。因此，索引是\"以空间换时间\"的典型策略，需根据实际读写比例合理设计。", "finish_reason": "stop", "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "max_tokens": 512, "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "ttft_s": 0.28372384200338274, "first_content_s": 3.9164422460016795, "elapsed_s": 10.166879840006004, "decode_tps_approx": 29.24182266761644, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789664067.137696, "event": "REQUEST_START", "name": "trace-prefill-32768", "profile": true, "prompt_tokens_preflight": 32742}
|
|
{"label": "eager", "time": 1789664086.9158142, "event": "RESULT", "name": "trace-prefill-32768", "profile": true, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32742, "total_tokens": 32809, "completion_tokens": 67, "completion_tokens_details": {"reasoning_tokens": 59}}, "max_tokens": 2048, "prompt_sha256": "464e9da0976ca56ddece006a237605bca8b60d3dd0aab538abbc0aaa1696815c", "output_sha256": "ca2e8f89b165bee277a12cac7bb1cbc8ce34eef2ee29ecd1a8a46aa71c502cfa", "ttft_s": 15.503820653997536, "first_content_s": 17.303895275996183, "elapsed_s": 19.650969089998398, "decode_tps_approx": 35.058139901273435, "metrics_delta": {"vllm:prefix_cache_queries_total": 32742.0, "vllm:prefix_cache_hits_total": 0.0}}
|
|
{"label": "eager", "time": 1789664086.9506161, "event": "REQUEST_START", "name": "trace-reuse-32768", "profile": true, "prompt_tokens_preflight": 32742}
|
|
{"label": "eager", "time": 1789664093.2510297, "event": "RESULT", "name": "trace-reuse-32768", "profile": true, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32742, "total_tokens": 32810, "completion_tokens": 68, "completion_tokens_details": {"reasoning_tokens": 60}}, "max_tokens": 2048, "prompt_sha256": "464e9da0976ca56ddece006a237605bca8b60d3dd0aab538abbc0aaa1696815c", "output_sha256": "ce351e2ffc5a1b2641f170a3fa56c81034b4d81226c524d10936eb65c7eb3926", "ttft_s": 1.385693889002141, "first_content_s": 3.091133230998821, "elapsed_s": 6.173271200997988, "decode_tps_approx": 37.499826794181516, "metrics_delta": {"vllm:prefix_cache_queries_total": 32742.0, "vllm:prefix_cache_hits_total": 30400.0}}
|
|
{"label": "eager", "time": 1789664093.251096, "event": "PROFILE_SUITE_PASS"}
|