{
  "tokenize(receiver)": {
    "mean_ms": 0.285680200004208,
    "p50_ms": 0.28286499997420833,
    "p95_ms": 0.29625649997342407,
    "n": 50.0
  },
  "infer x1": {
    "mean_ms": 20.3907745399988,
    "p50_ms": 20.329225000011775,
    "p95_ms": 20.864236499971867,
    "n": 50.0
  },
  "decide() x1": {
    "mean_ms": 20.359278120006365,
    "p50_ms": 20.330745499961722,
    "p95_ms": 20.485164500007613,
    "n": 50.0
  },
  "infer x16": {
    "mean_ms": 459.22972584000263,
    "p50_ms": 461.296622500015,
    "p95_ms": 472.11640399995076,
    "n": 50.0
  },
  "throughput_emails_per_sec": {
    "bs_1": 50.55320677490372,
    "bs_8": 33.17495789514291,
    "bs_32": 34.04478551894138
  },
  "device": "cpu",
  "benchmark_conditions": {
    "device": "cpu",
    "gpu_name": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
    "torch": "2.11.0+cu130",
    "cuda_available": true,
    "cuda_version": "13.0",
    "python": "3.13.15 (main, Aug  6 2026, 11:06:22) [GCC 13.3.0]",
    "max_length": 512,
    "reps_per_stage": 50,
    "warmup": 5,
    "pool_size": 64,
    "pool_source": "testbeds",
    "date_utc": "2026-10-16T02:48:52.151664+00:00"
  }
}