quantization_metrics.json

{
  "name": "quantize_and_save",
  "seconds": 71.19859568402171,
  "gpu_start_mib": 270,
  "gpu_end_mib": 312,
  "gpu_peak_mib": 1276,
  "torch_peak_allocated_mib": 870,
  "torch_peak_reserved_mib": 964,
  "base_model": "baidu/ERNIE-Image-Turbo",
  "output": "artifacts/ERNIE-Image-Turbo-SDNQ-uint4-static",
  "output_size_bytes": 10048077414,
  "recipe": {
    "weights_dtype": "uint4",
    "group_size": 0,
    "use_svd": false,
    "svd_rank": 32,
    "svd_steps": 8,
    "dynamic_loss_threshold": null,
    "use_quantized_matmul": false,
    "dequantize_fp32": false
  }
}