aparler/PyNorch
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

batched matmul cuda

Browse source
This commit is contained in:
lucasdelimanogueira 2024-05-16 19:34:58 -03:00
parent 82a854ff11
commit 5da5a7ad0d
4 changed files with 40 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
norch/csrc/tensor.cpp
View file

@ -695,7 +695,7 @@ extern "C" {
float* result_data;
cudaMalloc((void **)&result_data, size * sizeof(float));
//batched_matmul_tensor_cuda(tensor1, tensor2, result_data);
batched_matmul_tensor_cuda(tensor1, tensor2, result_data);
return create_tensor(result_data, shape, ndim, device);
}
else {