Home / Class/ QLinearUnpackWeightFp16Legacy Class — pytorch Architecture

QLinearUnpackWeightFp16Legacy Class — pytorch Architecture

Architecture documentation for the QLinearUnpackWeightFp16Legacy class in qlinear_unpack.cpp from the pytorch codebase.

Class cpp

Entity Profile

Source Code

aten/src/ATen/native/quantized/qlinear_unpack.cpp lines 54–63

class QLinearUnpackWeightFp16Legacy final {
 public:
  static std::tuple<at::Tensor, std::optional<Tensor>> run(
      const at::Tensor& packed_weight) {
    TORCH_CHECK(false,
        "quantized.linear_unpack(Tensor) is unsupported! Please "
        "upgrade your model to use the newer quantized.linear_"
        "unpack(LinearPackedParamsBase) overload");
  }
};

Source

Analyze Your Own Codebase

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

Try Supermodel Free