{
  "model": "models/YuE2-OrbitQuant-W4A4",
  "gemv": true,
  "fuse_packed": true,
  "replay": "benchmark/ru-original-full/run-00",
  "gpu": "NVIDIA GeForce RTX 5090",
  "results": [
    {
      "repeat": 0,
      "prefill_seconds": 1.1080292710103095,
      "wall_seconds": 2.194309923099354,
      "cuda_ms": 2194.27587890625,
      "tokens": 512,
      "tps": 233.33075907382553
    },
    {
      "repeat": 1,
      "prefill_seconds": 0.14538272097706795,
      "wall_seconds": 2.1817037297878414,
      "cuda_ms": 2181.6689453125,
      "tokens": 512,
      "tps": 234.67897726415362
    },
    {
      "repeat": 2,
      "prefill_seconds": 0.14446253678761423,
      "wall_seconds": 2.199943969026208,
      "cuda_ms": 2199.907958984375,
      "tokens": 512,
      "tps": 232.7332001217439
    }
  ]
}