Home / Class/ unwrap_vector Class — pytorch Architecture

unwrap_vector Class — pytorch Architecture

Architecture documentation for the unwrap_vector class in qlinear_deserialize.cpp from the pytorch codebase.

Class cpp

Entity Profile

Source Code

aten/src/ATen/native/ao_sparse/quantized/cpu/qlinear_deserialize.cpp lines 26–32

template <typename TENSOR_DTYPE, typename VEC_DTYPE>
std::vector<VEC_DTYPE> unwrap_vector(at::Tensor tensor) {
  std::vector<VEC_DTYPE> vec(tensor.numel());
  TENSOR_DTYPE* tensor_data_ptr = tensor.data_ptr<TENSOR_DTYPE>();
  std::copy(tensor_data_ptr, tensor_data_ptr + tensor.numel(), vec.data());
  return vec;
}

Source

Analyze Your Own Codebase

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

Try Supermodel Free