CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix CUDART_VERSION checks (#11821)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-12 13:16:39 +01:00
committed by GitHub
parent 369be5598a
commit c3d6af7cd2
3 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/common.cuh
View File

@@ -165,11 +165,11 @@ static const char * cu_get_error_str(CUresult err) {
#define CU_CHECK(err) CUDA_CHECK_GEN(err, CUDA_SUCCESS, cu_get_error_str)
#endif
#if CUDART_VERSION >= 11100 || defined(GGML_USE_MUSA)
#if CUDART_VERSION >= 11010 || defined(GGML_USE_MUSA)
#define GGML_CUDA_ASSUME(x) __builtin_assume(x)
#else
#define GGML_CUDA_ASSUME(x)
#endif // CUDART_VERSION >= 11100
#endif // CUDART_VERSION >= 11010
#ifdef GGML_CUDA_F16
typedef half dfloat; // dequantize float