tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-15 12:42:40 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cuda: Fix HIP build by adding define for __trap (#4569)

Browse Source 
Regression of 1398823922
HIP doesn't have trap, only abort
This commit is contained in:
arlo-phoenix
2023-12-21 20:13:25 +01:00
committed by GitHub
parent 8fe03ffdda
commit 562cf222b5
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-cuda.cu
View File

@@ -80,6 +80,7 @@
#define cudaStreamWaitEvent(stream, event, flags) hipStreamWaitEvent(stream, event, flags)
#define cudaStream_t hipStream_t
#define cudaSuccess hipSuccess
#define __trap abort
#else
#include <cuda_runtime.h>
#include <cublas_v2.h>