pytorch Architecture Docs
Home / Class/ dequantize_val Class — pytorch Architecture

dequantize_val Class — pytorch Architecture

Architecture documentation for the dequantize_val class in AffineQuantizerBase.cpp from the pytorch codebase.

Class cpp

Entity Profile

Source Code

aten/src/ATen/native/quantized/AffineQuantizerBase.cpp lines 98–104

template <typename T>
inline float dequantize_val(double scale, int64_t zero_point, T value) {
  fbgemm::TensorQuantizationParams qparams{};
  qparams.scale = static_cast<float>(scale);
  qparams.zero_point = static_cast<int32_t>(zero_point);
  return fbgemm::Dequantize<typename T::underlying>(value.val_, qparams);
}

Source

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free