docs(perf): profile CUDA graph coverage and PLE costs on Spark

This commit is contained in:
2026-09-18 01:22:13 +08:00
parent f1a8964072
commit d7e1e745c3
23 changed files with 8384 additions and 1 deletions
@@ -0,0 +1,39 @@
{"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"}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,823 @@
{
"file": "trace.2.sqlite",
"gpu_activity_span_s": 17.45799776,
"gpu_busy_union_s": 16.999974145,
"gpu_idle_within_span_s": 0.4580236150000019,
"kernel_count": 107899,
"graph_node_kernel_count": 0,
"api": {
"cudaStreamSynchronize_v3020": [
92,
6.388727359999995
],
"cuLaunchKernelEx": [
30313,
2.942097295999861
],
"cudaLaunchKernelExC_v11060": [
27262,
2.8157289279998983
],
"cudaLaunchKernel_v7000": [
34403,
2.1073674239999285
],
"cuLaunchKernel": [
15921,
0.18051391999999974
],
"cudaMemcpyAsync_v3020": [
2359,
0.02657009600000002
],
"cudaEventSynchronize_v3020": [
46,
0.01590248
],
"cudaEventRecordWithFlags_v11010": [
3413,
0.006630880000000002
],
"cudaMemsetAsync_v3020": [
736,
0.0055193599999999975
],
"cuTensorMapEncodeTiled": [
27416,
0.004886224000000271
],
"cuKernelGetFunction": [
15921,
0.0038959359999997194
],
"cudaGetDriverEntryPointByVersion_v12050": [
26496,
0.0037329280000005572
],
"cuKernelGetName": [
35159,
0.0033410560000001516
],
"cudaStreamWaitEvent_v3020": [
2588,
0.0021758880000000004
],
"cudaEventQuery_v3020": [
1494,
0.0019392639999999957
],
"cudaStreamIsCapturing_v10000": [
6960,
0.0014392959999999955
],
"cudaEventCreateWithFlags_v3020": [
92,
0.000234256
],
"cudaEventDestroy_v3020": [
92,
0.00018534400000000007
]
},
"nvtx": {
"PLE_lookup_tokens=1600": {
"count": 20,
"sum_s": 5.58014968,
"union_s": 5.58014968,
"gpu_overlap_s": 5.318215141
},
"PLE_wait_for_GPU": {
"count": 46,
"sum_s": 6.389229296,
"union_s": 6.389229296,
"gpu_overlap_s": 6.341070402
},
"PLE_CPU_dedup": {
"count": 46,
"sum_s": 0.01914024,
"union_s": 0.01914024,
"gpu_overlap_s": 0.0
},
"PLE_CPU_gather": {
"count": 46,
"sum_s": 0.275209776,
"union_s": 0.275209776,
"gpu_overlap_s": 0.0
},
"PLE_lookup_tokens=742": {
"count": 1,
"sum_s": 0.29896912,
"union_s": 0.29896912,
"gpu_overlap_s": 0.278459202
},
"PLE_lookup_tokens=3": {
"count": 25,
"sum_s": 0.820145456,
"union_s": 0.820145456,
"gpu_overlap_s": 0.746778411
}
},
"dispatch": {
"CG_DISPATCH:actual=1600:mode=NONE:padded=1600": 40,
"CG_DISPATCH:actual=1:mode=NONE:padded=1": 46,
"CG_DISPATCH:actual=742:mode=NONE:padded=742": 2,
"CG_DISPATCH:actual=3:mode=NONE:padded=3": 50
},
"dispatch_timeline": [
{
"start_ns": 45828672,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 415343408,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 441920176,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 467464272,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 1117406208,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 1146479600,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1170640896,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 1839789152,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 1870939456,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1896334032,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 2568046544,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 2598479856,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2624039184,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 3305750304,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 3335311984,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3361130160,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 4046256096,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 4076056912,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4101620656,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 4786128624,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 4816276720,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4842056960,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 5522623936,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 5552300720,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5576921440,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 6259346144,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 6290320240,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6315131568,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 7002476032,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 7032926192,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7058327584,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 7753655264,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 7785387856,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7811813408,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 8504434640,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 8535191696,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 8561506848,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 9253677696,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 9285233312,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 9311217936,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 10009614064,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 10040506016,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 10066581360,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 10757969120,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 10789570400,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 10815237984,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 11519444752,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 11550823200,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 11575788896,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 12278226144,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 12309497040,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 12335515504,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 13034051120,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 13066055552,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 13091963328,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 13790163952,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 13821175296,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 13846090352,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 14557613040,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 14589908560,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 14615422640,
"name": "CG_DISPATCH:actual=742:mode=NONE:padded=742"
},
{
"start_ns": 15203740016,
"name": "CG_DISPATCH:actual=742:mode=NONE:padded=742"
},
{
"start_ns": 15220760336,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15234841296,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15491074784,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15493643856,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15497135184,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15564983824,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15566982016,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15570203408,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15644290848,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15646296832,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15649329520,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15729121168,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15731019920,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15734338320,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15813356656,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15815902416,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15819264448,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15894042800,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15895960816,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15898832688,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15982235440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 15984929392,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 15988404656,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16064077552,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16066769024,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16070591120,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16140542304,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16142492784,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16145392256,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16230150416,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16232897584,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16236422000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16305893904,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16307780160,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16310441504,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16394138896,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16396838944,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16400267168,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16476712080,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16479446496,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16482904144,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16559135840,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16561788800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16565117088,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16632650032,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16634497504,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16637262864,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16722767040,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16725243152,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16728652272,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16807455696,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16810202752,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16813561920,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16894260000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16898134688,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16903894256,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16982500864,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 16985299840,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 16988503344,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17054985488,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17056901872,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 17059848448,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17143682800,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17146548688,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 17150240800,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17226658560,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17229352608,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 17233024096,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17306935664,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17308968096,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 17311992480,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17388634448,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17391419008,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 17394878992,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17463051952,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 17464913120,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
}
],
"top_kernels": [
[
"device_kernel",
[
4416,
5.785133960999994
]
],
[
"Kernel2",
[
15921,
1.6569721249999942
]
],
[
"_qsa_sparse_paged_gqa_splitk_kernel",
[
644,
1.481612926999999
]
],
[
"nvjet_sm121_tst_mma_128x208x64_2_32x104x64_tmaAB_bz_TNNN",
[
1000,
1.3622323199999982
]
],
[
"_hc_combine_norm_kernel",
[
4646,
0.8981812170000064
]
],
[
"kernel",
[
1510,
0.8489803810000001
]
],
[
"_hc_gate_mix_kernel",
[
4738,
0.6790835519999859
]
],
[
"nvjet_sm121_tst_mma_128x240x64_2_32x120x64_tmaAB_bz_TNNN",
[
980,
0.5484992310000006
]
],
[
"nvjet_sm121_tst_mma_128x128x64_3_32x64x64_tmaAB_bz_TNNN",
[
2000,
0.484882112
]
],
[
"finalizeMoeRoutingKernel",
[
2208,
0.4100567680000026
]
],
[
"_causal_conv1d_fwd_kernel",
[
756,
0.2423829440000001
]
],
[
"_fused_post_conv_kernel",
[
756,
0.23299334399999985
]
],
[
"doActivationKernel",
[
2208,
0.2290338470000007
]
],
[
"elementwise_kernel",
[
6060,
0.22898364799999965
]
],
[
"kernel_cutlass_kernel_flashinfergdn_kernelsdelta_rule_dsldelta_rule_sm120_FullyFusedDeltaRuleSm120_object_at__tensorptrf32gmemalign16o1_tensorptrf32gmemalign16o1_CopyAtom_ThrID10_TVLayout_0",
[
756,
0.19385532799999977
]
],
[
"vectorized_elementwise_kernel",
[
10976,
0.18249009600000335
]
],
[
"expandInputRowsKernel",
[
2208,
0.17563680399999979
]
],
[
"layer_norm_fwd_kernel",
[
756,
0.17546492700000002
]
],
[
"sm120_fp8_fp4_gemm_1d1d_impl",
[
184,
0.16484399999999996
]
],
[
"nvjet_sm121_tst_mma_128x192x64_2_32x96x64_tmaAB_bz_TNNN",
[
980,
0.13451315200000008
]
]
],
"notes": "GPU busy is interval union, not utilization counter. CPU/API/NVTX times overlap GPU work and each other; do not sum them as exclusive costs."
}
@@ -0,0 +1,583 @@
{
"file": "trace.3.sqlite",
"gpu_activity_span_s": 3.245924224,
"gpu_busy_union_s": 3.090907949,
"gpu_idle_within_span_s": 0.15501627499999993,
"kernel_count": 58496,
"graph_node_kernel_count": 0,
"api": {
"cudaStreamSynchronize_v3020": [
52,
1.0780331839999997
],
"cudaLaunchKernelExC_v11060": [
16696,
0.3360265120000019
],
"cuLaunchKernelEx": [
13138,
0.22730212800000002
],
"cudaLaunchKernel_v7000": [
16229,
0.21477230400000039
],
"cuLaunchKernel": [
12433,
0.05239439999999998
],
"cudaMemcpyAsync_v3020": [
939,
0.00983091199999999
],
"cudaEventSynchronize_v3020": [
26,
0.0089596
],
"cudaEventRecordWithFlags_v11010": [
2877,
0.004890783999999996
],
"cuKernelGetFunction": [
12433,
0.0027621279999998907
],
"cuTensorMapEncodeTiled": [
15496,
0.002756256000000075
],
"cudaMemsetAsync_v3020": [
416,
0.0023939039999999988
],
"cudaGetDriverEntryPointByVersion_v12050": [
14976,
0.001993504000000201
],
"cudaStreamWaitEvent_v3020": [
2430,
0.0018610560000000033
],
"cuKernelGetName": [
16301,
0.0014150560000001082
],
"cudaStreamIsCapturing_v10000": [
5810,
0.0011180959999999769
],
"cudaEventQuery_v3020": [
798,
0.001018544
],
"cudaEventCreateWithFlags_v3020": [
52,
0.000134192
],
"cudaEventDestroy_v3020": [
52,
0.00010068799999999997
]
},
"nvtx": {
"PLE_lookup_tokens=1600": {
"count": 1,
"sum_s": 0.018957376,
"union_s": 0.018957376,
"gpu_overlap_s": 0.011426528
},
"PLE_wait_for_GPU": {
"count": 26,
"sum_s": 1.078286144,
"union_s": 1.078286144,
"gpu_overlap_s": 1.058767637
},
"PLE_CPU_dedup": {
"count": 26,
"sum_s": 0.002243088,
"union_s": 0.002243088,
"gpu_overlap_s": 0.0
},
"PLE_CPU_gather": {
"count": 26,
"sum_s": 0.062812192,
"union_s": 0.062812192,
"gpu_overlap_s": 0.0
},
"PLE_lookup_tokens=742": {
"count": 1,
"sum_s": 0.292337536,
"union_s": 0.292337536,
"gpu_overlap_s": 0.279791319
},
"PLE_lookup_tokens=3": {
"count": 24,
"sum_s": 0.842259408,
"union_s": 0.842259408,
"gpu_overlap_s": 0.771610318
}
},
"dispatch": {
"CG_DISPATCH:actual=1600:mode=NONE:padded=1600": 2,
"CG_DISPATCH:actual=1:mode=NONE:padded=1": 26,
"CG_DISPATCH:actual=742:mode=NONE:padded=742": 2,
"CG_DISPATCH:actual=3:mode=NONE:padded=3": 48
},
"dispatch_timeline": [
{
"start_ns": 46439136,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 440098864,
"name": "CG_DISPATCH:actual=1600:mode=NONE:padded=1600"
},
{
"start_ns": 472554240,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 498029616,
"name": "CG_DISPATCH:actual=742:mode=NONE:padded=742"
},
{
"start_ns": 1080640368,
"name": "CG_DISPATCH:actual=742:mode=NONE:padded=742"
},
{
"start_ns": 1097925088,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1109689376,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1374741120,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1377837856,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1381724192,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1449909984,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1452632352,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1456060352,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1537442544,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1540106512,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1543362000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1622817104,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1625489424,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1628952064,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1697539568,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1699380000,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1702138000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1777756128,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1779549280,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1782099440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1865886816,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1868546304,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1872017632,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1939645984,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1941472672,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1944250112,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2021839712,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2023852576,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2026597104,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2103480432,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2105282848,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2107900064,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2193835440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2196580896,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2199840944,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2282745504,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2285692352,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2289777504,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2362513824,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2365324800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2368818832,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2436200000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2438187600,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2441020928,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2516737184,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2518684848,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2521416768,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2596916928,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2598750864,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2601295488,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2678072112,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2679938368,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2682459200,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2756745440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2758542912,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2761074960,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2838330208,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2840177632,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2842655760,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2918308832,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2920073040,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2922520640,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3006922960,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3008938128,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3011760224,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3094064288,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3096710352,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3100043552,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3174526160,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3177165152,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3180415120,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3257416576,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3260041984,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
}
],
"top_kernels": [
[
"Kernel2",
[
12433,
1.083779682999996
]
],
[
"device_kernel",
[
2496,
0.8852412400000004
]
],
[
"kernel",
[
360,
0.38886832
]
],
[
"_qsa_sparse_paged_gqa_splitk_kernel",
[
364,
0.12547817500000008
]
],
[
"_hc_combine_norm_kernel",
[
2626,
0.06954325899999982
]
],
[
"nvjet_sm121_tst_mma_128x208x64_2_32x104x64_tmaAB_bz_TNNN",
[
50,
0.068864416
]
],
[
"_hc_gate_mix_kernel",
[
2678,
0.04872185600000148
]
],
[
"finalizeMoeRoutingKernel",
[
1248,
0.03866553600000007
]
],
[
"sm120_fp8_fp4_gemm_1d1d_impl",
[
104,
0.038346688000000004
]
],
[
"nvjet_sm121_tst_mma_192x160x64_2_48x80x64_tmaAB_bz_TNNN",
[
51,
0.034701248
]
],
[
"nvjet_sm121_tst_mma_128x240x64_2_32x120x64_tmaAB_bz_TNNN",
[
49,
0.02691910399999999
]
],
[
"nvjet_sm121_tst_mma_128x128x64_3_32x64x64_tmaAB_bz_TNNN",
[
100,
0.024421632000000002
]
],
[
"gdn_decode_post_conv_mtp_kernel",
[
864,
0.023706272000000014
]
],
[
"expandInputRowsKernel",
[
1248,
0.022278243999999982
]
],
[
"doActivationKernel",
[
1248,
0.02122110900000002
]
],
[
"elementwise_kernel",
[
2004,
0.020444831999999843
]
],
[
"vectorized_elementwise_kernel",
[
5307,
0.018513366999999715
]
],
[
"_causal_conv1d_fwd_kernel",
[
72,
0.017434495999999997
]
],
[
"nvjet_sm121_tst_mma_128x224x64_2_64x56x64_tmaAB_bz_TNNN",
[
50,
0.016634912
]
],
[
"_fused_post_conv_kernel",
[
72,
0.015161888000000002
]
]
],
"notes": "GPU busy is interval union, not utilization counter. CPU/API/NVTX times overlap GPU work and each other; do not sum them as exclusive costs."
}