tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-28 21:23:55 -04:00
Code Issues Packages Projects Releases Wiki Activity

limit to GGML_ALLOW_CUDA_GRAPHS defined in llama.cpp cmake

Browse Source
This commit is contained in:
Alan Gray
2024-04-25 00:51:48 -07:00
parent 408759687f
commit 0640427f7b
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-cuda.cu
View File

@@ -2405,7 +2405,7 @@ GGML_CALL static void ggml_backend_cuda_synchronize(ggml_backend_t backend) {
GGML_UNUSED(backend);
}
#if (CUDART_VERSION >= 12000)
#if (CUDART_VERSION >= 12000) && defined(GGML_ALLOW_CUDA_GRAPHS)
#define USE_CUDA_GRAPH
#endif