optimization/benchmark.json

{
  "load_seconds": 2.426407459017355,
  "torch": "2.14.0+cu130",
  "gpu": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition",
  "fp8_linears": 224,
  "steps": 40,
  "cfg": 1,
  "extra_quantization": false,
  "approximate_cache": false,
  "timing": {
    "1024": {
      "seconds": [
        5.903008527995553,
        5.9249284460092895,
        5.935668507008813,
        5.946647913951892,
        5.951301124005113
      ],
      "mean": 5.932310903794132,
      "warmup_seconds": 11.555044600041583,
      "peak_gb": 32.590829568
    },
    "2048": {
      "seconds": [
        37.25538438500371,
        37.301657135016285,
        37.31008757499512
      ],
      "mean": 37.2890430316717,
      "warmup_seconds": 39.20627289195545,
      "peak_gb": 53.722432512
    }
  },
  "protocol": "CUDA synchronized; batch1; full40steps; includes encoder, denoising and VAE; excludes model load, resolution warmup and file writes. Weights and prefixKVcache unchanged. Compiled mode emulates intermediate precision casts."
}