File: frozen_linear_transpose.h

package info (click to toggle)
pytorch 1.13.1%2Bdfsg-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 139,252 kB
  • sloc: cpp: 1,100,274; python: 706,454; ansic: 83,052; asm: 7,618; java: 3,273; sh: 2,841; javascript: 612; makefile: 323; xml: 269; ruby: 185; yacc: 144; objc: 68; lex: 44
file content (13 lines) | stat: -rw-r--r-- 286 bytes parent folder | download 
1
2
3
4
5
6
7
8
9
10
11
12
13
 
#pragma once

#include <torch/csrc/jit/ir/ir.h>

namespace torch {
namespace jit {

// Transposes the weight matrix for frozen linear modules.
// and converts it into a matmul
TORCH_API bool FrozenLinearTranspose(std::shared_ptr<Graph>& graph);

} // namespace jit
} // namespace torch