record max batched tokens 32768 experiment

This commit is contained in:
2026-07-15 10:27:33 +08:00
parent 59e497fdc9
commit 2c7a8d12b3
2 changed files with 163 additions and 0 deletions

View File

@@ -0,0 +1,124 @@
{
"created_at": "2026-07-14T20:56:29",
"url": "http://127.0.0.1:1111",
"model": "llm",
"dataset": "/root/work/logs/synthetic_cumulative_8_s3_cap40k.jsonl",
"concurrency": 1,
"max_requests": 8,
"max_tokens": 256,
"wall_sec": 335.87523818574846,
"success_rate": 1.0,
"ttft_p90_sec": 13.004944081977008,
"output_tps_p10_per_request": 5.8948614972894635,
"aggregate_output_tps": 5.555634318502662,
"aggregate_input_tps_uncached": 173.43046874978486,
"aggregate_cache_tps": 497.94679983972844,
"cache_hit_rate": 0.7416795639891973,
"weighted_token_throughput": 857.5945239544665,
"totals": {
"requests": 8,
"success": 8,
"prompt_tokens": 225499,
"input_tokens_uncached": 58251,
"cached_tokens": 167248,
"completion_tokens": 1866,
"reasoning_tokens": 1731
},
"targets": {
"output_tps_p10_per_request_gte_20": false,
"ttft_p90_lte_5": false,
"cache_hit_rate_gte_50pct": true,
"success_rate_gte_99pct": true,
"weighted_token_throughput_gte_8000": false
},
"results": [
{
"ok": true,
"elapsed_sec": 27.413454679772258,
"ttft_sec": 7.43462404422462,
"prompt_tokens": 7498,
"cached_tokens": 0,
"completion_tokens": 168,
"reasoning_tokens": 82,
"output_tps": 8.40890055402359,
"error": null
},
{
"ok": true,
"elapsed_sec": 49.30410090461373,
"ttft_sec": 22.904547728598118,
"prompt_tokens": 34177,
"cached_tokens": 7488,
"completion_tokens": 162,
"reasoning_tokens": 113,
"output_tps": 6.136467497002161,
"error": null
},
{
"ok": true,
"elapsed_sec": 45.20640793628991,
"ttft_sec": 2.946982776746154,
"prompt_tokens": 35384,
"cached_tokens": 34160,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 6.05782021486361,
"error": null
},
{
"ok": true,
"elapsed_sec": 38.86536529287696,
"ttft_sec": 8.762256804853678,
"prompt_tokens": 19274,
"cached_tokens": 7472,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 8.504105152524406,
"error": null
},
{
"ok": true,
"elapsed_sec": 46.21588536910713,
"ttft_sec": 3.327174164354801,
"prompt_tokens": 37099,
"cached_tokens": 35376,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 5.968936645772505,
"error": null
},
{
"ok": true,
"elapsed_sec": 35.56211626343429,
"ttft_sec": 5.644598634913564,
"prompt_tokens": 14661,
"cached_tokens": 7472,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 8.556859669264544,
"error": null
},
{
"ok": true,
"elapsed_sec": 46.31439816579223,
"ttft_sec": 3.116101799532771,
"prompt_tokens": 38199,
"cached_tokens": 37088,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 5.926159629756877,
"error": null
},
{
"ok": true,
"elapsed_sec": 46.98421955294907,
"ttft_sec": 3.0118106845766306,
"prompt_tokens": 39207,
"cached_tokens": 38192,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 5.821832521532164,
"error": null
}
]
}