Files

40 lines
18 KiB
JSON

{"label": "graph", "time": 1789664773.0911076, "event": "REQUEST_START", "name": "warmup", "profile": false, "prompt_tokens_preflight": 51}
{"label": "graph", "time": 1789664774.6022928, "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": 0.6364480190022732, "first_content_s": 1.4175457309975172, "elapsed_s": 1.5047177029991872, "decode_tps_approx": 39.6877362766987, "metrics_delta": {"vllm:prefix_cache_queries_total": 51.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664774.614013, "event": "REQUEST_START", "name": "short-0", "profile": false, "prompt_tokens_preflight": 65}
{"label": "graph", "time": 1789664781.980255, "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": 0.32573997599683935, "first_content_s": 3.8834300599992275, "elapsed_s": 7.360314821999054, "decode_tps_approx": 30.279974628892248, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664781.9975877, "event": "REQUEST_START", "name": "prefill-8192-0", "profile": false, "prompt_tokens_preflight": 8173}
{"label": "graph", "time": 1789664788.1946163, "event": "RESULT", "name": "prefill-8192-0", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8247, "completion_tokens": 74, "completion_tokens_details": {"reasoning_tokens": 66}}, "max_tokens": 2048, "prompt_sha256": "f59f163e1c7bb8a79d08df830d94d6d2e98fec457e9de75e3c09f6fca7ab0813", "output_sha256": "c0d6109d7f5d6c6f5486e269f63ea0338562a90ab0ceeede5f228b020e701eea", "ttft_s": 3.921214998998039, "first_content_s": 6.03858627199952, "elapsed_s": 6.191493427999376, "decode_tps_approx": 33.338899955373805, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664788.2102215, "event": "REQUEST_START", "name": "reuse-8192-0", "profile": false, "prompt_tokens_preflight": 8173}
{"label": "graph", "time": 1789664791.047786, "event": "RESULT", "name": "reuse-8192-0", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8238, "completion_tokens": 65, "completion_tokens_details": {"reasoning_tokens": 57}}, "max_tokens": 2048, "prompt_sha256": "f59f163e1c7bb8a79d08df830d94d6d2e98fec457e9de75e3c09f6fca7ab0813", "output_sha256": "50530d055152bcaa11d1779a66b456a8ad5175a5343fb48f268c163f397d0089", "ttft_s": 0.8737782960015466, "first_content_s": 2.671151395996276, "elapsed_s": 2.8319971849996364, "decode_tps_approx": 34.055335354489465, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 6400.0}}
{"label": "graph", "time": 1789664791.096218, "event": "REQUEST_START", "name": "prefill-32768-0", "profile": false, "prompt_tokens_preflight": 32745}
{"label": "graph", "time": 1789664808.7936926, "event": "RESULT", "name": "prefill-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": 15.511759164000978, "first_content_s": 17.52370634300314, "elapsed_s": 17.691939716001798, "decode_tps_approx": 32.87688689931954, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664808.8368387, "event": "REQUEST_START", "name": "reuse-32768-0", "profile": false, "prompt_tokens_preflight": 32745}
{"label": "graph", "time": 1789664812.1356192, "event": "RESULT", "name": "reuse-32768-0", "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": "605f7b492252f50eaf60e8d128dde3f2d2e1b50dd26f0b45db88dac00e36a5ca", "output_sha256": "8b503330d6b70b8845bab80540601fc48c8f840d54d07f38d80250c8167de89f", "ttft_s": 1.325252010996337, "first_content_s": 3.1243166819986072, "elapsed_s": 3.293290553992847, "decode_tps_approx": 36.2184980346298, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 30400.0}}
{"label": "graph", "time": 1789664812.1429493, "event": "REQUEST_START", "name": "short-1", "profile": false, "prompt_tokens_preflight": 65}
{"label": "graph", "time": 1789664819.2091334, "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": 0.2600282569983392, "first_content_s": 3.7012813049950637, "elapsed_s": 7.060739258995454, "decode_tps_approx": 31.32107217692348, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664819.2247505, "event": "REQUEST_START", "name": "prefill-8192-1", "profile": false, "prompt_tokens_preflight": 8173}
{"label": "graph", "time": 1789664824.82708, "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": 3.7701075279983343, "first_content_s": 5.436177673000202, "elapsed_s": 5.596617848997994, "decode_tps_approx": 35.516432222041566, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664824.8427408, "event": "REQUEST_START", "name": "reuse-8192-1", "profile": false, "prompt_tokens_preflight": 8173}
{"label": "graph", "time": 1789664827.8556995, "event": "RESULT", "name": "reuse-8192-1", "profile": false, "correct": true, "content": "\n\n21573", "finish_reason": "stop", "usage": {"prompt_tokens": 8173, "total_tokens": 8247, "completion_tokens": 74, "completion_tokens_details": {"reasoning_tokens": 66}}, "max_tokens": 2048, "prompt_sha256": "6c13deb2d4ddee54db95d7ebc8a1b87d24ed8a4112c33644c18b6b5d61ad7a16", "output_sha256": "c0d6109d7f5d6c6f5486e269f63ea0338562a90ab0ceeede5f228b020e701eea", "ttft_s": 0.8690901810041396, "first_content_s": 2.8428866180038312, "elapsed_s": 3.0074559670028975, "decode_tps_approx": 35.510793077788634, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 6400.0}}
{"label": "graph", "time": 1789664827.8988104, "event": "REQUEST_START", "name": "prefill-32768-1", "profile": false, "prompt_tokens_preflight": 32745}
{"label": "graph", "time": 1789664845.1446679, "event": "RESULT", "name": "prefill-32768-1", "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": "0a5e4ba33ff264d180b8a56d89184c0fefad59a96fdd348d655bd54fe5b5ed45", "output_sha256": "8b503330d6b70b8845bab80540601fc48c8f840d54d07f38d80250c8167de89f", "ttft_s": 15.357147006005107, "first_content_s": 17.08089536800253, "elapsed_s": 17.239325528003974, "decode_tps_approx": 37.728914829613814, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664845.1907535, "event": "REQUEST_START", "name": "reuse-32768-1", "profile": false, "prompt_tokens_preflight": 32745}
{"label": "graph", "time": 1789664848.6512141, "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": 1.3272808809997514, "first_content_s": 3.296925946000556, "elapsed_s": 3.4540864679947845, "decode_tps_approx": 33.71980234098872, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 30400.0}}
{"label": "graph", "time": 1789664848.660781, "event": "REQUEST_START", "name": "short-2", "profile": false, "prompt_tokens_preflight": 65}
{"label": "graph", "time": 1789664855.73135, "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": 0.2623967160034226, "first_content_s": 3.7147180649990332, "elapsed_s": 7.0642776130043785, "decode_tps_approx": 31.315723764990278, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664855.7496016, "event": "REQUEST_START", "name": "prefill-8192-2", "profile": false, "prompt_tokens_preflight": 8173}
{"label": "graph", "time": 1789664861.4250884, "event": "RESULT", "name": "prefill-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": 3.768740819999948, "first_content_s": 5.512005377000605, "elapsed_s": 5.670499198000471, "decode_tps_approx": 37.32072215199369, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664861.4389272, "event": "REQUEST_START", "name": "reuse-8192-2", "profile": false, "prompt_tokens_preflight": 8173}
{"label": "graph", "time": 1789664864.1561685, "event": "RESULT", "name": "reuse-8192-2", "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": "b49f6dbbf80f49ad860a60b0a7c58dfc2122e38bb8493ae155790f22305d8f7a", "output_sha256": "09d17d110b06ec13d532382c41ea29955b7edfa8dd4bd34163a08fa746e56610", "ttft_s": 0.8816422219970264, "first_content_s": 2.543782171997009, "elapsed_s": 2.711807350999152, "decode_tps_approx": 35.522341967132114, "metrics_delta": {"vllm:prefix_cache_queries_total": 8173.0, "vllm:prefix_cache_hits_total": 6400.0}}
{"label": "graph", "time": 1789664864.196416, "event": "REQUEST_START", "name": "prefill-32768-2", "profile": false, "prompt_tokens_preflight": 32745}
{"label": "graph", "time": 1789664881.472875, "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": 15.375977513001999, "first_content_s": 17.108021717001975, "elapsed_s": 17.268514374001825, "decode_tps_approx": 37.54862656190945, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664881.5214229, "event": "REQUEST_START", "name": "reuse-32768-2", "profile": false, "prompt_tokens_preflight": 32745}
{"label": "graph", "time": 1789664884.7351754, "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": 1.3270910260034725, "first_content_s": 3.045836498000426, "elapsed_s": 3.2060768180017476, "decode_tps_approx": 37.82214005937634, "metrics_delta": {"vllm:prefix_cache_queries_total": 32745.0, "vllm:prefix_cache_hits_total": 30400.0}}
{"label": "graph", "time": 1789664884.7446704, "event": "REQUEST_START", "name": "trace-short", "profile": true, "prompt_tokens_preflight": 65}
{"label": "graph", "time": 1789664894.3422408, "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": 0.23192091599776177, "first_content_s": 3.732794447001652, "elapsed_s": 9.19204898099997, "decode_tps_approx": 30.944518883030874, "metrics_delta": {"vllm:prefix_cache_queries_total": 65.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664894.3764791, "event": "REQUEST_START", "name": "trace-prefill-32768", "profile": true, "prompt_tokens_preflight": 32742}
{"label": "graph", "time": 1789664914.0692568, "event": "RESULT", "name": "trace-prefill-32768", "profile": true, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32742, "total_tokens": 32812, "completion_tokens": 70, "completion_tokens_details": {"reasoning_tokens": 62}}, "max_tokens": 2048, "prompt_sha256": "464e9da0976ca56ddece006a237605bca8b60d3dd0aab538abbc0aaa1696815c", "output_sha256": "7eec57291da7ee95ae6d9214f8ed940a405e64beb9f49a4693387362aac3e14c", "ttft_s": 15.522943222997128, "first_content_s": 17.421024231000047, "elapsed_s": 19.56250263000402, "decode_tps_approx": 34.818013845987785, "metrics_delta": {"vllm:prefix_cache_queries_total": 32742.0, "vllm:prefix_cache_hits_total": 0.0}}
{"label": "graph", "time": 1789664914.1044817, "event": "REQUEST_START", "name": "trace-reuse-32768", "profile": true, "prompt_tokens_preflight": 32742}
{"label": "graph", "time": 1789664920.2165241, "event": "RESULT", "name": "trace-reuse-32768", "profile": true, "correct": true, "content": "\n\n90812", "finish_reason": "stop", "usage": {"prompt_tokens": 32742, "total_tokens": 32816, "completion_tokens": 74, "completion_tokens_details": {"reasoning_tokens": 66}}, "max_tokens": 2048, "prompt_sha256": "464e9da0976ca56ddece006a237605bca8b60d3dd0aab538abbc0aaa1696815c", "output_sha256": "997501e1996b1c37af707622b1c4caf8dba93113e868f28210bd47ba700b5804", "ttft_s": 1.3475809320007102, "first_content_s": 3.358952419999696, "elapsed_s": 5.983986291001202, "decode_tps_approx": 34.79999075012843, "metrics_delta": {"vllm:prefix_cache_queries_total": 32742.0, "vllm:prefix_cache_hits_total": 30400.0}}
{"label": "graph", "time": 1789664920.2165873, "event": "PROFILE_SUITE_PASS"}