icer/qwen36_01
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
qwen36_01/worklogs/remote_results/2026-07-15-official-like-baseline/driver_b8192.log

231 lines
8.7 KiB
Plaintext
Raw Permalink Blame History

[exp] label=batched_tokens_8192_20260715
[exp] max_num_batched_tokens=8192
[exp] out_dir=/root/work/logs/batched_tokens_8192_20260715
Wed Jul 15 02:34:25 UTC 2026
[exp] stopping existing api_server
[exp] gpu before start
Timestamp Wed Jul 15 02:34:25 2026
+-----------------------------------------------------------------------------+
| IX-ML: 3.2.3 Driver Version: 3.2.1 CUDA Version: 10.2 |
|-------------------------------+----------------------+----------------------|
| GPU Name | Bus-Id | Clock-SM Clock-Mem |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Iluvatar BI-V100 | 00000000:4B:00.0 | 1500MHz 1200MHz |
| 0% 29C P0 47W / 250W | 257MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 Iluvatar BI-V100 | 00000000:4C:00.0 | 1500MHz 1200MHz |
| 0% 32C P0 47W / 250W | 257MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 Iluvatar BI-V100 | 00000000:4D:00.0 | 1500MHz 1200MHz |
| 0% 31C P0 47W / 250W | 257MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 3 Iluvatar BI-V100 | 00000000:4E:00.0 | 1500MHz 1200MHz |
| 0% 30C P0 47W / 250W | 257MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Process name Usage(MiB) |
|=============================================================================|
| No running processes found |
+-----------------------------------------------------------------------------+
[exp] starting server
[exp] server_pid=32482
[exp] waiting for health
[exp] health ok after 17 checks
[exp] running benchmark
done 1/8 ok=True
done 2/8 ok=True
done 3/8 ok=True
done 4/8 ok=True
done 5/8 ok=True
done 6/8 ok=True
done 7/8 ok=True
done 8/8 ok=True
{
"created_at": "2026-07-15T02:41:32",
"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": 345.89166797697544,
"success_rate": 1.0,
"ttft_p90_sec": 13.995924570597705,
"output_tps_p10_per_request": 5.840174878063855,
"aggregate_output_tps": 5.513286894574578,
"aggregate_input_tps_uncached": 168.40821966222535,
"aggregate_cache_tps": 483.5271140764599,
"cache_hit_rate": 0.7416795639891973,
"weighted_token_throughput": 834.7509573986608,
"totals": {
"requests": 8,
"success": 8,
"prompt_tokens": 225499,
"input_tokens_uncached": 58251,
"cached_tokens": 167248,
"completion_tokens": 1907,
"reasoning_tokens": 1758
},
"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
}
}
RESULT_FILE /root/work/logs/batched_tokens_8192_20260715/eager_100k_b8192_c1_r8_t256_cap40k.json
[exp] benchmark rc=0
{
"created_at": "2026-07-15T02:41:32",
"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": 345.89166797697544,
"success_rate": 1.0,
"ttft_p90_sec": 13.995924570597705,
"output_tps_p10_per_request": 5.840174878063855,
"aggregate_output_tps": 5.513286894574578,
"aggregate_input_tps_uncached": 168.40821966222535,
"aggregate_cache_tps": 483.5271140764599,
"cache_hit_rate": 0.7416795639891973,
"weighted_token_throughput": 834.7509573986608,
"totals": {
"requests": 8,
"success": 8,
"prompt_tokens": 225499,
"input_tokens_uncached": 58251,
"cached_tokens": 167248,
"completion_tokens": 1907,
"reasoning_tokens": 1758
},
"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": 36.67137165553868,
"ttft_sec": 7.283070221543312,
"prompt_tokens": 7498,
"cached_tokens": 0,
"completion_tokens": 250,
"reasoning_tokens": 147,
"output_tps": 8.506786299354092,
"error": null
},
{
"ok": true,
"elapsed_sec": 42.85823520086706,
"ttft_sec": 23.074742704629898,
"prompt_tokens": 34177,
"cached_tokens": 7488,
"completion_tokens": 121,
"reasoning_tokens": 75,
"output_tps": 6.116210270912193,
"error": null
},
{
"ok": true,
"elapsed_sec": 46.396307623013854,
"ttft_sec": 3.7564049027860165,
"prompt_tokens": 35384,
"cached_tokens": 34160,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 6.003766042330974,
"error": null
},
{
"ok": true,
"elapsed_sec": 40.55220231600106,
"ttft_sec": 10.105002513155341,
"prompt_tokens": 19274,
"cached_tokens": 7472,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 8.407998162644606,
"error": null
},
{
"ok": true,
"elapsed_sec": 47.4568429403007,
"ttft_sec": 4.107830764725804,
"prompt_tokens": 37099,
"cached_tokens": 35376,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 5.90555556290724,
"error": null
},
{
"ok": true,
"elapsed_sec": 36.76491709984839,
"ttft_sec": 6.331659993156791,
"prompt_tokens": 14661,
"cached_tokens": 7472,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 8.411850203957014,
"error": null
},
{
"ok": true,
"elapsed_sec": 47.44748286344111,
"ttft_sec": 3.74263353087008,
"prompt_tokens": 38199,
"cached_tokens": 37088,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 5.85747357351524,
"error": null
},
{
"ok": true,
"elapsed_sec": 47.73618622124195,
"ttft_sec": 3.59681879542768,
"prompt_tokens": 39207,
"cached_tokens": 38192,
"completion_tokens": 256,
"reasoning_tokens": 256,
"output_tps": 5.799811255343957,
"error": null
}
]
}[exp] gpu after benchmark
Timestamp Wed Jul 15 02:41:32 2026
+-----------------------------------------------------------------------------+
| IX-ML: 3.2.3 Driver Version: 3.2.1 CUDA Version: 10.2 |
|-------------------------------+----------------------+----------------------|
| GPU Name | Bus-Id | Clock-SM Clock-Mem |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Iluvatar BI-V100 | 00000000:4B:00.0 | 1500MHz 1200MHz |
| 0% 33C P0 64W / 250W | 29967MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 Iluvatar BI-V100 | 00000000:4C:00.0 | 1500MHz 1200MHz |
| 0% 36C P0 63W / 250W | 29906MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 Iluvatar BI-V100 | 00000000:4D:00.0 | 1500MHz 1200MHz |
| 0% 36C P0 62W / 250W | 29910MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 3 Iluvatar BI-V100 | 00000000:4E:00.0 | 1500MHz 1200MHz |
| 0% 34C P0 61W / 250W | 29770MiB / 32768MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Process name Usage(MiB) |
|=============================================================================|
+-----------------------------------------------------------------------------+
Reference in New Issue View Git Blame Copy Permalink