[exp] label=moe_summary_profile_20260715
[exp] max_num_batched_tokens=16384
[exp] out_dir=/root/work/logs/moe_summary_profile_20260715
Wed Jul 15 02:49:29 UTC 2026
[exp] stopping existing api_server
[exp] gpu before start
Timestamp    Wed Jul 15 02:49:37 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=33749
[exp] waiting for health
[exp] health ok after 18 checks
[exp] running benchmark
done 1/2 ok=True
done 2/2 ok=True
{
  "created_at": "2026-07-15T02:52:28",
  "url": "http://127.0.0.1:1111",
  "model": "llm",
  "dataset": "/root/work/logs/synthetic_cumulative_8_s3_cap40k.jsonl",
  "concurrency": 1,
  "max_requests": 2,
  "max_tokens": 256,
  "wall_sec": 84.45088295079768,
  "success_rate": 1.0,
  "ttft_p90_sec": 20.33267523739487,
  "output_tps_p10_per_request": 5.792271822208015,
  "aggregate_output_tps": 4.4641333142679605,
  "aggregate_input_tps_uncached": 404.8151873073707,
  "aggregate_cache_tps": 88.66692375925328,
  "cache_hit_rate": 0.1796760647870426,
  "weighted_token_throughput": 1257.7107697249571,
  "totals": {
    "requests": 2,
    "success": 2,
    "prompt_tokens": 41675,
    "input_tokens_uncached": 34187,
    "cached_tokens": 7488,
    "completion_tokens": 377,
    "reasoning_tokens": 285
  },
  "targets": {
    "output_tps_p10_per_request_gte_20": false,
    "ttft_p90_lte_5": false,
    "cache_hit_rate_gte_50pct": false,
    "success_rate_gte_99pct": true,
    "weighted_token_throughput_gte_8000": false
  }
}
RESULT_FILE /root/work/logs/moe_summary_profile_20260715/eager_100k_b16384_c1_r2_t256_cap40k.json
[exp] benchmark rc=0
{
  "created_at": "2026-07-15T02:52:28",
  "url": "http://127.0.0.1:1111",
  "model": "llm",
  "dataset": "/root/work/logs/synthetic_cumulative_8_s3_cap40k.jsonl",
  "concurrency": 1,
  "max_requests": 2,
  "max_tokens": 256,
  "wall_sec": 84.45088295079768,
  "success_rate": 1.0,
  "ttft_p90_sec": 20.33267523739487,
  "output_tps_p10_per_request": 5.792271822208015,
  "aggregate_output_tps": 4.4641333142679605,
  "aggregate_input_tps_uncached": 404.8151873073707,
  "aggregate_cache_tps": 88.66692375925328,
  "cache_hit_rate": 0.1796760647870426,
  "weighted_token_throughput": 1257.7107697249571,
  "totals": {
    "requests": 2,
    "success": 2,
    "prompt_tokens": 41675,
    "input_tokens_uncached": 34187,
    "cached_tokens": 7488,
    "completion_tokens": 377,
    "reasoning_tokens": 285
  },
  "targets": {
    "output_tps_p10_per_request_gte_20": false,
    "ttft_p90_lte_5": false,
    "cache_hit_rate_gte_50pct": false,
    "success_rate_gte_99pct": true,
    "weighted_token_throughput_gte_8000": false
  },
  "results": [
    {
      "ok": true,
      "elapsed_sec": 41.03028617054224,
      "ttft_sec": 7.251164922490716,
      "prompt_tokens": 7498,
      "cached_tokens": 0,
      "completion_tokens": 256,
      "reasoning_tokens": 210,
      "output_tps": 7.578645936941501,
      "error": null
    },
    {
      "ok": true,
      "elapsed_sec": 43.417322823777795,
      "ttft_sec": 21.78617638349533,
      "prompt_tokens": 34177,
      "cached_tokens": 7488,
      "completion_tokens": 121,
      "reasoning_tokens": 75,
      "output_tps": 5.59378580945985,
      "error": null
    }
  ]
}[exp] gpu after benchmark
Timestamp    Wed Jul 15 02:52:28 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    61W / 250W   | 30143MiB / 32768MiB  | 0%        Default    |
+-------------------------------+----------------------+----------------------+
| 1    Iluvatar BI-V100         | 00000000:4C:00.0     | 1500MHz   1200MHz    |
| 0%   35C   P0    60W / 250W   | 30082MiB / 32768MiB  | 0%        Default    |
+-------------------------------+----------------------+----------------------+
| 2    Iluvatar BI-V100         | 00000000:4D:00.0     | 1500MHz   1200MHz    |
| 0%   35C   P0    60W / 250W   | 30086MiB / 32768MiB  | 0%        Default    |
+-------------------------------+----------------------+----------------------+
| 3    Iluvatar BI-V100         | 00000000:4E:00.0     | 1500MHz   1200MHz    |
| 0%   34C   P0    58W / 250W   | 29946MiB / 32768MiB  | 0%        Default    |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU        PID      Process name                                Usage(MiB) |
|=============================================================================|
+-----------------------------------------------------------------------------+