apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 17:11:21 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

init (#6642)

Browse Source 
Co-authored-by: gongweibao <gognweibao@baidu.com>
This commit is contained in:
gongweibao
2026-03-04 21:55:31 +08:00
committed by GitHub
parent 5c8f5184d9
commit ddb06ff83f
306 changed files with 40627 additions and 34418 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/gpu_ops/common/cudaUtils.h
+12 -12
View File
@@ -16,18 +16,18 @@
#include <cuda_runtime.h>
#include "paddle/phi/core/enforce.h"
namespace common
{
namespace common {
inline int getSMVersion()
{
int device{-1};
PADDLE_ENFORCE_GPU_SUCCESS(cudaGetDevice(&device));
int sm_major = 0;
int sm_minor = 0;
PADDLE_ENFORCE_GPU_SUCCESS(cudaDeviceGetAttribute(&sm_major, cudaDevAttrComputeCapabilityMajor, device));
PADDLE_ENFORCE_GPU_SUCCESS(cudaDeviceGetAttribute(&sm_minor, cudaDevAttrComputeCapabilityMinor, device));
return sm_major * 10 + sm_minor;
inline int getSMVersion() {
int device{-1};
PADDLE_ENFORCE_GPU_SUCCESS(cudaGetDevice(&device));
int sm_major = 0;
int sm_minor = 0;
PADDLE_ENFORCE_GPU_SUCCESS(cudaDeviceGetAttribute(
&sm_major, cudaDevAttrComputeCapabilityMajor, device));
PADDLE_ENFORCE_GPU_SUCCESS(cudaDeviceGetAttribute(
&sm_minor, cudaDevAttrComputeCapabilityMinor, device));
return sm_major * 10 + sm_minor;
}
}
} // namespace common