QLinearInt8 Class — pytorch Architecture

Source Code

aten/src/ATen/native/ao_sparse/quantized/cpu/qlinear.cpp lines 233–246

class QLinearInt8 final {
 public:
  static at::Tensor run(
      const at::Tensor& input,
      const c10::intrusive_ptr<LinearPackedParamsBase>& packed_weight,
      double output_scale,
      int64_t output_zero_point) {
    if (ReluFused) {
      return packed_weight->apply_relu(input, output_scale, output_zero_point);
    } else {
      return packed_weight->apply(input, output_scale, output_zero_point);
    }
  }
};