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

check METAX_GPU (#5114)

Browse Source
This commit is contained in:
chen
2025-11-19 16:02:21 +08:00
committed by GitHub
parent de43577a7c
commit 9ff418db73
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
custom_ops/gpu_ops/helper.h
View File

@@ -725,6 +725,10 @@ inline void launchWithPdlWhenEnabled(KernelFn kernelFn,
size_t dynamicShmSize,
cudaStream_t stream,
Args &&...args) {
#ifdef PADDLE_WITH_CUSTOM_DEVICE_METAX_GPU
(*kernelFn)<<<grid, block, dynamicShmSize, stream>>>(
std::forward<Args>(args)...);
#else
cudaLaunchConfig_t kernelConfig;
kernelConfig.gridDim = grid;
kernelConfig.blockDim = block;
@@ -738,5 +742,6 @@ inline void launchWithPdlWhenEnabled(KernelFn kernelFn,
kernelConfig.numAttrs = 1;
cudaLaunchKernelEx(&kernelConfig, kernelFn, std::forward<Args>(args)...);
#endif
}
#endif