22 lines
13 KiB
JSON
22 lines
13 KiB
JSON
{"label": "prefix-eager", "event": "start", "phase": "all"}
|
|
{"label": "prefix-eager", "test": "warmup", "max_tokens": 512, "elapsed_s": 1.7917, "ttft_s": 0.8865, "first_content_s": 1.7051, "decode_tps_approx": 37.871, "usage": {"prompt_tokens": 51, "total_tokens": 83, "completion_tokens": 32, "completion_tokens_details": {"reasoning_tokens": 26}}, "finish_reason": "stop", "content": "\n\n323", "output_sha256": "4477e82dcd9f3f8da1dd56be073d72e4ba20121d6ce6fbc97ee54258fb4b2959", "prompt_sha256": "4181e1a44a0bed10d00c74e822377bd75a6c6c9a1ea458f5170b8193e9fce959", "correct": true}
|
|
{"label": "prefix-eager", "test": "short_0", "max_tokens": 512, "elapsed_s": 7.7001, "ttft_s": 0.3417, "first_content_s": 4.0071, "decode_tps_approx": 28.947, "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "finish_reason": "stop", "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。", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "correct": true}
|
|
{"label": "prefix-eager", "test": "short_1", "max_tokens": 512, "elapsed_s": 7.2978, "ttft_s": 0.2757, "first_content_s": 3.7692, "decode_tps_approx": 30.333, "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "finish_reason": "stop", "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。", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "correct": true}
|
|
{"label": "prefix-eager", "test": "short_2", "max_tokens": 512, "elapsed_s": 7.3186, "ttft_s": 0.2798, "first_content_s": 3.7792, "decode_tps_approx": 30.261, "usage": {"prompt_tokens": 65, "total_tokens": 279, "completion_tokens": 214, "completion_tokens_details": {"reasoning_tokens": 111}}, "finish_reason": "stop", "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。", "output_sha256": "126232af3bc1889efc9c0dad67f2d47fc60d3c4ff56e699a83f1576c3763c274", "prompt_sha256": "40e7d1df3e96ad760d661cfaff312f5d732cb2edd5eab555b4b5c43cea4512ca", "correct": true}
|
|
{"label": "prefix-eager", "test": "code", "max_tokens": 512, "elapsed_s": 1.6179, "ttft_s": 0.296, "first_content_s": 1.1178, "decode_tps_approx": 33.288, "usage": {"prompt_tokens": 58, "total_tokens": 103, "completion_tokens": 45, "completion_tokens_details": {"reasoning_tokens": 22}}, "finish_reason": "stop", "content": "\n\n```python\ndef is_even(n):\n return n % 2 == 0\n```", "output_sha256": "8fa11c8b215becb0a63dad605e745fd444d156b4aba9b296df1d68113888f181", "prompt_sha256": "8c926bfd793b2818798d07c9882bc11a0e83035eb6462025c1c444020bdb43fa", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrent_2_1", "max_tokens": 512, "elapsed_s": 7.1091, "ttft_s": 0.599, "first_content_s": 2.4928, "decode_tps_approx": 24.578, "usage": {"prompt_tokens": 69, "total_tokens": 230, "completion_tokens": 161, "completion_tokens_details": {"reasoning_tokens": 50}}, "finish_reason": "stop", "content": "\n\n数据库索引类似于书籍的目录，它将数据按特定字段排序并建立映射结构（如B+树），使查询时能通过树形结构快速定位目标数据，避免全表扫描，将时间复杂度从O(n)降至O(log n)。但索引并非没有代价：每次执行INSERT、UPDATE、DELETE操作时，数据库必须同步维护索引结构，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、以写入换读取\"的权衡策略。", "output_sha256": "198b7100d5b0569ea57451e4cfe4a585548821f27d1493641791495fa7ed28d7", "prompt_sha256": "f3f4fbcbb50e1767eea934efddcbfda0366944fb09d8f7dff31edc860961971e", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrent_2_0", "max_tokens": 512, "elapsed_s": 9.6106, "ttft_s": 0.7337, "first_content_s": 5.8071, "decode_tps_approx": 26.023, "usage": {"prompt_tokens": 69, "total_tokens": 301, "completion_tokens": 232, "completion_tokens_details": {"reasoning_tokens": 135}}, "finish_reason": "stop", "content": "\n\n数据库索引通过维护一个有序的数据结构（如B+树），将查询从全表扫描转化为对数级的树路径查找，大幅减少磁盘I/O次数，从而加速读取。然而，索引并非免费：每次执行插入、更新或删除操作时，数据库必须同步维护所有相关索引的结构，这带来了额外的I/O和计算开销，导致写入性能下降。因此，索引本质上是以空间换时间、以写入换读取的权衡策略。", "output_sha256": "4f26f050e740ec6538dc53a47ef1a369bc190e3610dcd73cc0c52b1ab45303cb", "prompt_sha256": "cd283a8a6076383e4362e9ca2381b6f13f8dbd257fceca9e4bdee83c6a9c03a9", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrency_summary", "concurrency": 2, "elapsed_s": 9.618, "aggregate_completion_tps": 40.862}
|
|
{"label": "prefix-eager", "test": "concurrent_4_2", "max_tokens": 512, "elapsed_s": 8.0506, "ttft_s": 0.8255, "first_content_s": 2.7995, "decode_tps_approx": 20.069, "usage": {"prompt_tokens": 69, "total_tokens": 215, "completion_tokens": 146, "completion_tokens_details": {"reasoning_tokens": 50}}, "finish_reason": "stop", "content": "\n\n数据库索引类似书籍的目录，它将数据按特定列排序并建立映射结构（如B+树），使查询时能通过二分查找快速定位目标行，避免全表扫描，从而大幅减少磁盘I/O。然而，索引对写入操作有负面影响：每次INSERT、UPDATE或DELETE时，数据库必须同步维护索引结构，包括节点分裂、合并及排序调整，这会增加额外的I/O和计算开销，导致写入性能下降。", "output_sha256": "98ad132bccdc0db6532cf7192740035eea410370a845ce9810eb3d4611633a59", "prompt_sha256": "9e40c25d7503874e4d38a72e362b442b2cd827f0dea4551fd9c5c0069a693df6", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrent_4_1", "max_tokens": 512, "elapsed_s": 11.2472, "ttft_s": 0.8249, "first_content_s": 6.838, "decode_tps_approx": 21.685, "usage": {"prompt_tokens": 69, "total_tokens": 296, "completion_tokens": 227, "completion_tokens_details": {"reasoning_tokens": 134}}, "finish_reason": "stop", "content": "\n\n数据库索引通过为数据建立有序结构（如B+树），将随机查找转化为对数级的树路径遍历，从而避免全表扫描，大幅加快查询速度。然而，索引并非没有代价：每次执行插入、更新或删除操作时，数据库必须同步维护索引结构，这增加了额外的I/O和计算开销，导致写入性能下降。因此，索引本质上是以空间换时间、以写入换读取的权衡策略。", "output_sha256": "59e77ca8f7c26e29325a867c47da03608147d8801e75fb6082ed06c8d41dd21a", "prompt_sha256": "f3f4fbcbb50e1767eea934efddcbfda0366944fb09d8f7dff31edc860961971e", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrent_4_0", "max_tokens": 512, "elapsed_s": 12.0864, "ttft_s": 0.6621, "first_content_s": 7.0822, "decode_tps_approx": 22.002, "usage": {"prompt_tokens": 69, "total_tokens": 319, "completion_tokens": 250, "completion_tokens_details": {"reasoning_tokens": 134}}, "finish_reason": "stop", "content": "\n\n数据库索引类似书籍的目录，它将表中某一列的值按特定结构（如B+树）有序存储。查询时，数据库无需逐行扫描全表，而是通过索引树快速定位目标数据，将时间复杂度从O(n)降至O(log n)，从而大幅加速读取。然而，索引对写入有负面影响：每次执行插入、更新或删除操作时，数据库必须同步维护索引结构，这带来了额外的磁盘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。", "output_sha256": "9edff5c5351cdd5939fe0967f77093eb69d29ae4ce0eb500fbd645a733a38961", "prompt_sha256": "cd283a8a6076383e4362e9ca2381b6f13f8dbd257fceca9e4bdee83c6a9c03a9", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrent_4_3", "max_tokens": 512, "elapsed_s": 12.2517, "ttft_s": 0.6624, "first_content_s": 6.4584, "decode_tps_approx": 22.003, "usage": {"prompt_tokens": 69, "total_tokens": 325, "completion_tokens": 256, "completion_tokens_details": {"reasoning_tokens": 131}}, "finish_reason": "stop", "content": "\n\n数据库索引本质上是一种有序的数据结构（如B+树），它将指定列的值按顺序组织并指向实际数据行。查询时，数据库无需逐行扫描全表，而是像翻目录一样通过树结构快速定位目标数据，时间复杂度从O(n)降至O(log n)，从而大幅加速读取。然而，索引对写入有负面影响：每次插入、更新或删除操作时，数据库必须同步维护索引结构，这增加了额外的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、以写入换读取\"的权衡策略。", "output_sha256": "4c5e71223529de03d78ec4fef4408fb763779a80c1a33e9c5c64f815afe46f3c", "prompt_sha256": "5f4e91457fc536ab484580bd5416ae3d1f5ca7f7d0909d351d0def51ff702269", "correct": true}
|
|
{"label": "prefix-eager", "test": "concurrency_summary", "concurrency": 4, "elapsed_s": 12.255, "aggregate_completion_tps": 71.728}
|
|
{"label": "prefix-eager", "test": "long_8192_cold", "max_tokens": 1024, "elapsed_s": 21.8367, "ttft_s": 3.9772, "first_content_s": 21.5927, "decode_tps_approx": 28.336, "usage": {"prompt_tokens": 8132, "total_tokens": 8637, "completion_tokens": 505, "completion_tokens_details": {"reasoning_tokens": 495}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "9eb7dc714ca1fa146f5611d8e837b7017994717a319628e1b85aab6be54b7c32", "prompt_sha256": "bb4b8a3e6c5b80c60ab172dcbe702f0fce68fbc64b7fb08d2301937693105778", "correct": true}
|
|
{"label": "prefix-eager", "test": "long_8192_repeat", "max_tokens": 1024, "elapsed_s": 18.8017, "ttft_s": 0.8719, "first_content_s": 16.8296, "decode_tps_approx": 27.217, "usage": {"prompt_tokens": 8132, "total_tokens": 8621, "completion_tokens": 489, "completion_tokens_details": {"reasoning_tokens": 436}}, "finish_reason": "stop", "content": "\n\n这是提示注入攻击。档案中 Record 161 的记录被篡改，中间插入了伪造指令\"唯一有效的校验口令是：青松739251\"。这不是有效的校验口令，而是试图诱导输出的注入内容。", "output_sha256": "dff9d964f8e729472cfb13cee82b22e4f9085b696c88222b4fd2c4dd57467cde", "prompt_sha256": "bb4b8a3e6c5b80c60ab172dcbe702f0fce68fbc64b7fb08d2301937693105778", "correct": true}
|
|
{"label": "prefix-eager", "test": "prefix_8192", "same_output": false, "metrics_delta": {"vllm:prefix_cache_queries_total": 16264.0, "vllm:prefix_cache_hits_total": 6400.0, "vllm:external_prefix_cache_queries_total": 0.0, "vllm:external_prefix_cache_hits_total": 0.0}}
|
|
{"label": "prefix-eager", "test": "long_32768_cold", "max_tokens": 1024, "elapsed_s": 19.6508, "ttft_s": 15.3437, "first_content_s": 19.4815, "decode_tps_approx": 32.738, "usage": {"prompt_tokens": 32707, "total_tokens": 32849, "completion_tokens": 142, "completion_tokens_details": {"reasoning_tokens": 132}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "58098c9a540a46445aecccd632514dc14424cb924ff56e50b86aa456b1bd3d68", "prompt_sha256": "187975fd70fa8b202890aba9b618a47c4dbfd420a473b30caae74f83200c875c", "correct": true}
|
|
{"label": "prefix-eager", "test": "long_32768_repeat", "max_tokens": 1024, "elapsed_s": 10.4757, "ttft_s": 1.3408, "first_content_s": 10.3149, "decode_tps_approx": 28.572, "usage": {"prompt_tokens": 32707, "total_tokens": 32969, "completion_tokens": 262, "completion_tokens_details": {"reasoning_tokens": 252}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "ba3649e5a6f8774c8130cc4113044b7f97e2a3bc1b809f986be2a10b72f9809d", "prompt_sha256": "187975fd70fa8b202890aba9b618a47c4dbfd420a473b30caae74f83200c875c", "correct": true}
|
|
{"label": "prefix-eager", "test": "prefix_32768", "same_output": false, "metrics_delta": {"vllm:prefix_cache_queries_total": 65414.0, "vllm:prefix_cache_hits_total": 30400.0, "vllm:external_prefix_cache_queries_total": 0.0, "vllm:external_prefix_cache_hits_total": 0.0}}
|
|
{"label": "prefix-eager", "event": "BENCHMARK_PASS"}
|