File size: 1,333 Bytes
ec9a6bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

#include <ATen/ATen.h>
#include <torch/extension.h>

torch::Tensor fused_bias_act_op(const torch::Tensor &input,

                                const torch::Tensor &bias,

                                const torch::Tensor &refer, int act, int grad,

                                float alpha, float scale);

#define CHECK_CUDA(x)                                                          \
  TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
#define CHECK_CONTIGUOUS(x)                                                    \
  TORCH_CHECK(x.is_contiguous(), #x " must be contiguous")
#define CHECK_INPUT(x)                                                         \
  CHECK_CUDA(x);                                                               \
  CHECK_CONTIGUOUS(x)

torch::Tensor fused_bias_act(const torch::Tensor &input,
                             const torch::Tensor &bias,
                             const torch::Tensor &refer, int act, int grad,
                             float alpha, float scale) {
  CHECK_INPUT(input);
  CHECK_INPUT(bias);

  at::DeviceGuard guard(input.device());

  return fused_bias_act_op(input, bias, refer, act, grad, alpha, scale);
}

PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
  m.def("fused_bias_act", &fused_bias_act, "fused bias act (CUDA)");
}