add decode throughput analysis

This commit is contained in:
2026-07-14 17:11:28 +08:00
parent b41e7cd899
commit 465a9c8995
11 changed files with 2960 additions and 0 deletions

View File

@@ -0,0 +1,66 @@
{
"created_at": "2026-07-14T08:00:25",
"label": "full_parser_short_c1_t256_r3",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "short",
"with_tools": false,
"tool_count": 0,
"concurrency": 1,
"requests": 3,
"max_tokens": 256,
"wall_sec": 92.0443243663758,
"success_rate": 1.0,
"ttft_p50_sec": 1.0909903924912214,
"ttft_p90_sec": 1.8471774261444807,
"output_tps_p10_per_request": 8.736438485385,
"output_tps_p50_per_request": 8.738006408510326,
"aggregate_output_tps": 8.343806153033741,
"prompt_tokens": 117,
"cached_tokens": 64,
"completion_tokens": 768,
"reasoning_tokens": 768,
"chars": 2635,
"monitor": {
"records": 92,
"parsed_samples": 0
},
"results": [
{
"ok": true,
"elapsed_sec": 31.292513709515333,
"ttft_sec": 2.0362241845577955,
"completion_tokens": 256,
"prompt_tokens": 39,
"cached_tokens": 0,
"reasoning_tokens": 256,
"output_tps": 8.750255215433768,
"chars": 916,
"error": null
},
{
"ok": true,
"elapsed_sec": 30.353378538042307,
"ttft_sec": 1.0560779832303524,
"completion_tokens": 256,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 256,
"output_tps": 8.738006408510326,
"chars": 856,
"error": null
},
{
"ok": true,
"elapsed_sec": 30.394863702356815,
"ttft_sec": 1.0909903924912214,
"completion_tokens": 256,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 256,
"output_tps": 8.736046504603667,
"chars": 863,
"error": null
}
]
}

View File

@@ -0,0 +1,63 @@
{
"created_at": "2026-07-14T08:11:04",
"label": "full_parser_tool_c1_t128_r3",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "tool",
"with_tools": true,
"tool_count": 29,
"concurrency": 1,
"requests": 3,
"max_tokens": 128,
"wall_sec": 52.042631950229406,
"success_rate": 1.0,
"ttft_p50_sec": 1.0516742002218962,
"ttft_p90_sec": 4.98421496860683,
"output_tps_p10_per_request": 8.700721568035489,
"output_tps_p50_per_request": 8.704939531751927,
"aggregate_output_tps": 7.378566102637461,
"prompt_tokens": 6639,
"cached_tokens": 4416,
"completion_tokens": 384,
"reasoning_tokens": 384,
"chars": 1309,
"monitor": null,
"results": [
{
"ok": true,
"elapsed_sec": 20.671645294874907,
"ttft_sec": 5.967350160703063,
"completion_tokens": 128,
"prompt_tokens": 2213,
"cached_tokens": 0,
"reasoning_tokens": 128,
"output_tps": 8.704939531751927,
"chars": 445,
"error": null
},
{
"ok": true,
"elapsed_sec": 15.636568604037166,
"ttft_sec": 1.0516742002218962,
"completion_tokens": 128,
"prompt_tokens": 2213,
"cached_tokens": 2208,
"reasoning_tokens": 128,
"output_tps": 8.776203409914055,
"chars": 456,
"error": null
},
{
"ok": true,
"elapsed_sec": 15.731618992984295,
"ttft_sec": 1.018412284553051,
"completion_tokens": 128,
"prompt_tokens": 2213,
"cached_tokens": 2208,
"reasoning_tokens": 128,
"output_tps": 8.699667077106378,
"chars": 408,
"error": null
}
]
}

View File

@@ -0,0 +1,75 @@
{
"created_at": "2026-07-14T08:34:26",
"label": "noparser_short_c1_t128_r4",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "short",
"with_tools": false,
"tool_count": 0,
"concurrency": 1,
"requests": 4,
"max_tokens": 128,
"wall_sec": 64.02519051544368,
"success_rate": 1.0,
"ttft_p50_sec": 0.7723927367478609,
"ttft_p90_sec": 0.7913718132302165,
"output_tps_p10_per_request": 8.304385542911493,
"output_tps_p50_per_request": 8.42998946937195,
"aggregate_output_tps": 7.99685242446095,
"prompt_tokens": 156,
"cached_tokens": 128,
"completion_tokens": 512,
"reasoning_tokens": 0,
"chars": 1827,
"monitor": null,
"results": [
{
"ok": true,
"elapsed_sec": 16.272426838055253,
"ttft_sec": 0.7992097493261099,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 8.272358570683828,
"chars": 474,
"error": null
},
{
"ok": true,
"elapsed_sec": 15.848933763802052,
"ttft_sec": 0.7730832956731319,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 8.490399945966447,
"chars": 449,
"error": null
},
{
"ok": true,
"elapsed_sec": 16.047778205946088,
"ttft_sec": 0.7717021778225899,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 8.379115144776051,
"chars": 452,
"error": null
},
{
"ok": true,
"elapsed_sec": 15.853784639388323,
"ttft_sec": 0.7609824072569609,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 8.480863793967849,
"chars": 452,
"error": null
}
]
}

View File

@@ -0,0 +1,63 @@
{
"created_at": "2026-07-14T08:23:01",
"label": "noparser_short_c1_t256_r3",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "short",
"with_tools": false,
"tool_count": 0,
"concurrency": 1,
"requests": 3,
"max_tokens": 256,
"wall_sec": 97.52940320037305,
"success_rate": 1.0,
"ttft_p50_sec": 0.8136040437966585,
"ttft_p90_sec": 3.1817516405135393,
"output_tps_p10_per_request": 8.295711129981452,
"output_tps_p50_per_request": 8.327121469734012,
"aggregate_output_tps": 7.874548339254703,
"prompt_tokens": 117,
"cached_tokens": 64,
"completion_tokens": 768,
"reasoning_tokens": 0,
"chars": 2635,
"monitor": null,
"results": [
{
"ok": true,
"elapsed_sec": 34.66234661638737,
"ttft_sec": 3.7737885396927595,
"completion_tokens": 256,
"prompt_tokens": 39,
"cached_tokens": 0,
"reasoning_tokens": 0,
"output_tps": 8.287858545043312,
"chars": 916,
"error": null
},
{
"ok": true,
"elapsed_sec": 31.533973263576627,
"ttft_sec": 0.7910567671060562,
"completion_tokens": 256,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 8.327121469734012,
"chars": 856,
"error": null
},
{
"ok": true,
"elapsed_sec": 31.330975525081158,
"ttft_sec": 0.8136040437966585,
"completion_tokens": 256,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 8.388664802176624,
"chars": 863,
"error": null
}
]
}

View File

@@ -0,0 +1,75 @@
{
"created_at": "2026-07-14T08:35:37",
"label": "noparser_short_c2_t128_r4",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "short",
"with_tools": false,
"tool_count": 0,
"concurrency": 2,
"requests": 4,
"max_tokens": 128,
"wall_sec": 70.80830597691238,
"success_rate": 1.0,
"ttft_p50_sec": 0.9245951194316149,
"ttft_p90_sec": 0.9249729935079813,
"output_tps_p10_per_request": 3.6832897295816034,
"output_tps_p50_per_request": 3.7126825201316764,
"aggregate_output_tps": 7.230790130284175,
"prompt_tokens": 156,
"cached_tokens": 128,
"completion_tokens": 512,
"reasoning_tokens": 0,
"chars": 1816,
"monitor": null,
"results": [
{
"ok": true,
"elapsed_sec": 35.12894960306585,
"ttft_sec": 0.9234285913407803,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.742085961974495,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 35.12996072135866,
"ttft_sec": 0.9242945611476898,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.7420700827891884,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 35.67656988278031,
"ttft_sec": 0.925006128847599,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.683287489056221,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 35.67638896778226,
"ttft_sec": 0.9248956777155399,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.683294957474164,
"chars": 454,
"error": null
}
]
}

View File

@@ -0,0 +1,84 @@
{
"created_at": "2026-07-14T08:56:17",
"label": "noparser_short_c2_t128_r4_monitor",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "short",
"with_tools": false,
"tool_count": 0,
"concurrency": 2,
"requests": 4,
"max_tokens": 128,
"wall_sec": 69.160331716761,
"success_rate": 1.0,
"ttft_p50_sec": 0.9177342765033245,
"ttft_p90_sec": 0.9243953077122569,
"output_tps_p10_per_request": 3.7938414669033445,
"output_tps_p50_per_request": 3.8028299895382536,
"aggregate_output_tps": 7.4030876846693445,
"prompt_tokens": 156,
"cached_tokens": 128,
"completion_tokens": 512,
"reasoning_tokens": 0,
"chars": 1816,
"monitor": {
"records": 52,
"parsed_samples": 208,
"avg_gpu_util_pct": 28.91346153846154,
"max_gpu_util_pct": 100,
"avg_mem_mib": 30477.0,
"max_mem_mib": 30555,
"avg_power_w": 49.67307692307692,
"max_power_w": 51
},
"results": [
{
"ok": true,
"elapsed_sec": 34.663240656256676,
"ttft_sec": 0.9245693255215883,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.7938660578905252,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 34.66297300904989,
"ttft_sec": 0.9239892661571503,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.793830927908839,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 34.49104499258101,
"ttft_sec": 0.9110554531216621,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.811793921185982,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 34.491438234224916,
"ttft_sec": 0.9114792868494987,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 3.811797393814395,
"chars": 454,
"error": null
}
]
}

View File

@@ -0,0 +1,75 @@
{
"created_at": "2026-07-14T08:37:18",
"label": "noparser_short_c4_t128_r4",
"url": "http://127.0.0.1:1111",
"model": "llm",
"prompt_mode": "short",
"with_tools": false,
"tool_count": 0,
"concurrency": 4,
"requests": 4,
"max_tokens": 128,
"wall_sec": 100.87516433186829,
"success_rate": 1.0,
"ttft_p50_sec": 26.261823972687125,
"ttft_p90_sec": 51.59956250209361,
"output_tps_p10_per_request": 2.5736346925937763,
"output_tps_p50_per_request": 2.585721667979742,
"aggregate_output_tps": 5.075580331305096,
"prompt_tokens": 156,
"cached_tokens": 128,
"completion_tokens": 512,
"reasoning_tokens": 0,
"chars": 1846,
"monitor": null,
"results": [
{
"ok": true,
"elapsed_sec": 50.6585742700845,
"ttft_sec": 0.9234585296362638,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 2.573634304341249,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 50.65938341990113,
"ttft_sec": 0.9242926891893148,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 2.5736355985163404,
"chars": 486,
"error": null
},
{
"ok": true,
"elapsed_sec": 100.87196587957442,
"ttft_sec": 51.59965132176876,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 2.597807737443144,
"chars": 454,
"error": null
},
{
"ok": true,
"elapsed_sec": 100.8716309145093,
"ttft_sec": 51.599355256184936,
"completion_tokens": 128,
"prompt_tokens": 39,
"cached_tokens": 32,
"reasoning_tokens": 0,
"output_tps": 2.597809788360666,
"chars": 452,
"error": null
}
]
}