File: AsyncMM.cuh

package info (click to toggle)
pytorch-cuda 2.6.0%2Bdfsg-7
  • links: PTS, VCS
  • area: contrib
  • in suites: forky, sid, trixie
  • size: 161,620 kB
  • sloc: python: 1,278,832; cpp: 900,322; ansic: 82,710; asm: 7,754; java: 3,363; sh: 2,811; javascript: 2,443; makefile: 597; ruby: 195; xml: 84; objc: 68
file content (20 lines) | stat: -rw-r--r-- 402 bytes parent folder | download | duplicates (3) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
 
#pragma once
#include <ATen/core/TensorBase.h>
#include <optional>

namespace c10d::cuda::detail {

at::Tensor async_input_mm_out(
    at::Tensor a,
    at::Tensor b,
    at::Tensor a_chunk_signals,
    int64_t begin_chunk,
    at::Tensor out);

at::Tensor async_input_mm(
    at::Tensor a,
    at::Tensor b,
    at::Tensor a_chunk_signals,
    int64_t begin_chunk);

} // namespace c10d::cuda::detail