22 lines
13 KiB
JSON
22 lines
13 KiB
JSON
{"label": "graph-2048-3", "event": "start", "phase": "all"}
|
|
{"label": "graph-2048-3", "test": "warmup", "max_tokens": 512, "elapsed_s": 1.1031, "ttft_s": 0.2234, "first_content_s": 1.0211, "decode_tps_approx": 38.862, "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": "graph-2048-3", "test": "short_0", "max_tokens": 512, "elapsed_s": 7.1079, "ttft_s": 0.278, "first_content_s": 3.7342, "decode_tps_approx": 31.187, "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": "graph-2048-3", "test": "short_1", "max_tokens": 512, "elapsed_s": 7.0916, "ttft_s": 0.2719, "first_content_s": 3.737, "decode_tps_approx": 31.234, "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": "graph-2048-3", "test": "short_2", "max_tokens": 512, "elapsed_s": 7.0879, "ttft_s": 0.279, "first_content_s": 3.7342, "decode_tps_approx": 31.283, "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": "graph-2048-3", "test": "code", "max_tokens": 512, "elapsed_s": 1.5342, "ttft_s": 0.2776, "first_content_s": 1.0625, "decode_tps_approx": 35.02, "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": "graph-2048-3", "test": "concurrent_2_0", "max_tokens": 512, "elapsed_s": 6.1931, "ttft_s": 0.2949, "first_content_s": 1.9756, "decode_tps_approx": 26.28, "usage": {"prompt_tokens": 69, "total_tokens": 225, "completion_tokens": 156, "completion_tokens_details": {"reasoning_tokens": 49}}, "finish_reason": "stop", "content": "\n\n数据库索引类似于书籍的目录，它将数据按特定列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)。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\"的权衡策略。", "output_sha256": "56ab3bb5a8980ce544ea0b96f32ea33b7011ec652cb1b178aba054b32e8a126b", "prompt_sha256": "cd283a8a6076383e4362e9ca2381b6f13f8dbd257fceca9e4bdee83c6a9c03a9", "correct": true}
|
|
{"label": "graph-2048-3", "test": "concurrent_2_1", "max_tokens": 512, "elapsed_s": 6.7015, "ttft_s": 0.2954, "first_content_s": 2.066, "decode_tps_approx": 25.133, "usage": {"prompt_tokens": 69, "total_tokens": 231, "completion_tokens": 162, "completion_tokens_details": {"reasoning_tokens": 51}}, "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或DELETE时，数据库必须同步维护索引结构，这会增加额外的磁盘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、以写入换读取\"的权衡策略。", "output_sha256": "f30a47683579f5d00a57a223183883a0c42faab96b8ff61a78754870adbae62a", "prompt_sha256": "f3f4fbcbb50e1767eea934efddcbfda0366944fb09d8f7dff31edc860961971e", "correct": true}
|
|
{"label": "graph-2048-3", "test": "concurrency_summary", "concurrency": 2, "elapsed_s": 6.705, "aggregate_completion_tps": 47.428}
|
|
{"label": "graph-2048-3", "test": "concurrent_4_0", "max_tokens": 512, "elapsed_s": 6.9218, "ttft_s": 0.3262, "first_content_s": 2.0475, "decode_tps_approx": 20.924, "usage": {"prompt_tokens": 69, "total_tokens": 208, "completion_tokens": 139, "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，增加了额外开销，导致写入速度变慢，同时也会占用更多存储空间。", "output_sha256": "b98cfc1fb7c99b8757d62c90e5eb7f948fae2d558dc22d22dd5f6e22cceec32d", "prompt_sha256": "cd283a8a6076383e4362e9ca2381b6f13f8dbd257fceca9e4bdee83c6a9c03a9", "correct": true}
|
|
{"label": "graph-2048-3", "test": "concurrent_4_3", "max_tokens": 512, "elapsed_s": 7.6554, "ttft_s": 0.3263, "first_content_s": 2.1535, "decode_tps_approx": 20.74, "usage": {"prompt_tokens": 69, "total_tokens": 222, "completion_tokens": 153, "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，避免全表逐行扫描，从而大幅缩短检索时间。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\"的权衡策略。", "output_sha256": "50a1cc358ded216736e1b5abf1f4b7bbf5a41d6f4342f0a9241a54ce800f14ee", "prompt_sha256": "5f4e91457fc536ab484580bd5416ae3d1f5ca7f7d0909d351d0def51ff702269", "correct": true}
|
|
{"label": "graph-2048-3", "test": "concurrent_4_1", "max_tokens": 512, "elapsed_s": 9.7221, "ttft_s": 0.326, "first_content_s": 5.63, "decode_tps_approx": 23.308, "usage": {"prompt_tokens": 69, "total_tokens": 289, "completion_tokens": 220, "completion_tokens_details": {"reasoning_tokens": 132}}, "finish_reason": "stop", "content": "\n\n数据库索引通过为指定列建立有序的数据结构（如B+树），使查询时能像翻目录一样快速定位目标行，避免全表逐行扫描，从而大幅缩短查询时间。然而，索引并非没有代价：每次执行插入、更新或删除操作时，数据库都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，因此索引越多，写入性能下降越明显。", "output_sha256": "748e3ce7b823533e712b4bfe4a267c1810b2dc9c921b39df76b3407f866943b2", "prompt_sha256": "f3f4fbcbb50e1767eea934efddcbfda0366944fb09d8f7dff31edc860961971e", "correct": true}
|
|
{"label": "graph-2048-3", "test": "concurrent_4_2", "max_tokens": 512, "elapsed_s": 10.6131, "ttft_s": 0.3261, "first_content_s": 5.7489, "decode_tps_approx": 24.206, "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INSERT、UPDATE或DELETE时，数据库必须同步维护索引结构，增加额外的磁盘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\"的权衡策略。", "output_sha256": "c9168c5ef6ad370b85d6ca2f1fd68a014d00d82c74cd4d71c35a2b2f897f1cd5", "prompt_sha256": "9e40c25d7503874e4d38a72e362b442b2cd827f0dea4551fd9c5c0069a693df6", "correct": true}
|
|
{"label": "graph-2048-3", "test": "concurrency_summary", "concurrency": 4, "elapsed_s": 10.617, "aggregate_completion_tps": 71.773}
|
|
{"label": "graph-2048-3", "test": "long_8192_cold", "max_tokens": 2048, "elapsed_s": 11.4617, "ttft_s": 0.8288, "first_content_s": 11.3099, "decode_tps_approx": 28.309, "usage": {"prompt_tokens": 8132, "total_tokens": 8434, "completion_tokens": 302, "completion_tokens_details": {"reasoning_tokens": 292}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "95db4162763382030cd75f91a4ab6f9d55484e696934231c06a8985306d04a91", "prompt_sha256": "bb4b8a3e6c5b80c60ab172dcbe702f0fce68fbc64b7fb08d2301937693105778", "correct": true}
|
|
{"label": "graph-2048-3", "test": "long_8192_repeat", "max_tokens": 2048, "elapsed_s": 3.3733, "ttft_s": 0.8712, "first_content_s": 3.1331, "decode_tps_approx": 32.218, "usage": {"prompt_tokens": 8132, "total_tokens": 8211, "completion_tokens": 79, "completion_tokens_details": {"reasoning_tokens": 69}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "6a6e4b2ae4a2491d342096b635f66a3f9b228a6d434549c064bf0555182a04fe", "prompt_sha256": "bb4b8a3e6c5b80c60ab172dcbe702f0fce68fbc64b7fb08d2301937693105778", "correct": true}
|
|
{"label": "graph-2048-3", "test": "prefix_8192", "same_output": false, "metrics_delta": {"vllm:prefix_cache_queries_total": 16264.0, "vllm:prefix_cache_hits_total": 12800.0, "vllm:external_prefix_cache_queries_total": 0.0, "vllm:external_prefix_cache_hits_total": 0.0}}
|
|
{"label": "graph-2048-3", "test": "long_32768_cold", "max_tokens": 2048, "elapsed_s": 4.8807, "ttft_s": 1.3049, "first_content_s": 4.7197, "decode_tps_approx": 31.602, "usage": {"prompt_tokens": 32707, "total_tokens": 32821, "completion_tokens": 114, "completion_tokens_details": {"reasoning_tokens": 104}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "d71c1dffebd12f4ccf253342e764e4d81e292cde14f6b5ba3c912d4572abfe16", "prompt_sha256": "187975fd70fa8b202890aba9b618a47c4dbfd420a473b30caae74f83200c875c", "correct": true}
|
|
{"label": "graph-2048-3", "test": "long_32768_repeat", "max_tokens": 2048, "elapsed_s": 4.8809, "ttft_s": 1.3172, "first_content_s": 4.7252, "decode_tps_approx": 32.551, "usage": {"prompt_tokens": 32707, "total_tokens": 32824, "completion_tokens": 117, "completion_tokens_details": {"reasoning_tokens": 107}}, "finish_reason": "stop", "content": "\n\n青松739251", "output_sha256": "c220d72aac8e821e08b304da2fc6c3f4a97d813bd24608fe43654f9f0143ea6e", "prompt_sha256": "187975fd70fa8b202890aba9b618a47c4dbfd420a473b30caae74f83200c875c", "correct": true}
|
|
{"label": "graph-2048-3", "test": "prefix_32768", "same_output": false, "metrics_delta": {"vllm:prefix_cache_queries_total": 65414.0, "vllm:prefix_cache_hits_total": 60800.0, "vllm:external_prefix_cache_queries_total": 0.0, "vllm:external_prefix_cache_hits_total": 0.0}}
|
|
{"label": "graph-2048-3", "event": "BENCHMARK_COMPLETED"}
|