variant:
  id: onnx_int8
  format: onnx
  precision: int8            # INT8 quantized — auto-cast by NPU execution provider at runtime
  method: onnx_export        # base model exported to ONNX; quantization applied by runtime

quantization:
  datatype: int8
  scope:
    - weights
    - activations
  granularity: per-tensor    # typical for runtime-cast INT8
  calibration: ptq           # post-training quantization applied by the NPU EP / MWMX toolchain
  toolchain: onnx