apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

dcu adapter ernie45t (#2756)

Browse Source 
Co-authored-by: lifu <lifu@sugon.com>
Co-authored-by: yongqiangma <xing.wo@163.com>
This commit is contained in:
lifulll
2025-07-09 18:56:27 +08:00
committed by GitHub
parent 03a74995b8
commit 1f28bdf994
30 changed files with 1133 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
custom_ops/gpu_ops/share_external_data.cu
View File

@@ -37,10 +37,18 @@ std::vector<paddle::Tensor> ShareExternalData(paddle::Tensor& input,
}
shm = (volatile shmStruct *)info.addr;
void *ptr = nullptr;
#ifdef PADDLE_WITH_HIP
checkCudaErrors(
hipIpcOpenMemHandle(&ptr,
*(hipIpcMemHandle_t *)&shm->memHandle, // NOLINT
hipIpcMemLazyEnablePeerAccess));
#else
checkCudaErrors(
cudaIpcOpenMemHandle(&ptr,
*(cudaIpcMemHandle_t *)&shm->memHandle, // NOLINT
cudaIpcMemLazyEnablePeerAccess));
#endif
paddle::Tensor tmp_tensor = paddle::from_blob(
ptr,
shape,