optimization/baseline-benchmark.json

{
  "load_seconds": 2.426567278977018,
  "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": [
        6.9087469020159915,
        6.936133738025092
      ],
      "mean": 6.9224403200205415,
      "warmup_seconds": 8.378067673009355,
      "peak_gb": 32.590829568
    },
    "2048": {
      "seconds": [
        44.079785163048655,
        44.1227304089698
      ],
      "mean": 44.10125778600923,
      "warmup_seconds": 43.912163228029385,
      "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."
}