{
  "base_model": "sand-ai/MAGI-2-preview",
  "base_revision": "2dea51b64db47ee5b4402d36fd90829a0c58913b",
  "component": "preview",
  "quant_method": "fp8",
  "dtype": "float8_e4m3fn",
  "scheme": "weight-only; one fp32 scale per (flattened head-expert row, output channel) = amax over the reduction dim / 448; round to nearest",
  "quantized_tensors": ["*.moe_mlp.W_gate", "*.moe_mlp.W_up", "*.moe_mlp.W_down"],
  "scale_key_suffix": "_scale",
  "scale_dtype": "float32",
  "scale_shapes": {"W_gate": "(rows, d_expert)", "W_up": "(rows, d_expert)", "W_down": "(rows, d_head)"},
  "unchanged": "every other tensor, bf16 or fp32 as shipped",
  "compute": "MAGI2_FP8_MOE=w8a8 (default): expert inputs quantized to FP8 per (token, head), SwiGLU7 output at a fixed scale of 8, FP8 x FP8 -> fp32 tensor-core GEMMs on K-major weights; w8a16: FP8 tiles widened to bf16, bf16 x bf16 -> fp32",
  "code": "magi2_fp8/ (quantize.py, fp8_moe.py, patch.py, entry.py, check_kernel.py)"
}