root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-09-22 21:16:20 +00:00
Code Issues Actions 16 Packages Projects Releases Wiki Activity

mtgpu: enable unified memory

Browse Source 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
Xiaodong Ye 2024-09-22 12:49:37 +08:00
parent 43ff5f36c2
commit a3ad2c9971
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda.cu
View File

@ -136,7 +136,7 @@ static cudaError_t ggml_cuda_device_malloc(void ** ptr, size_t size, int device)
return res;
#else
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
#if !defined(GGML_USE_HIPBLAS)
cudaError_t err;
if (getenv("GGML_CUDA_ENABLE_UNIFIED_MEMORY") != nullptr)
{
@ -149,7 +149,7 @@ static cudaError_t ggml_cuda_device_malloc(void ** ptr, size_t size, int device)
return err;
#else
return cudaMalloc(ptr, size);
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
#endif // !defined(GGML_USE_HIPBLAS)
#endif
}

1
ggml/src/ggml-cuda/vendors/musa.h vendored
View File

@ -56,6 +56,7 @@
#define cudaLaunchHostFunc musaLaunchHostFunc
#define cudaMalloc musaMalloc
#define cudaMallocHost musaMallocHost
#define cudaMallocManaged musaMallocManaged
#define cudaMemcpy musaMemcpy
#define cudaMemcpyAsync musaMemcpyAsync
#define cudaMemcpyPeerAsync musaMemcpyPeerAsync