CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-18 11:46:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: Volta tensor core support for MMF (#16843)

Browse Source 
* CUDA: Volta tensor core support for MMF

* more generic checks for hardware support

* Update ggml/src/ggml-cuda/mmf.cuh

Co-authored-by: Aman Gupta <amangupta052@gmail.com>

---------

Co-authored-by: Aman Gupta <amangupta052@gmail.com>
This commit is contained in:
Johannes Gäßler
2025-10-31 15:57:19 +01:00
committed by GitHub
parent 6d39015a74
commit 31c511a968
4 changed files with 254 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/src/ggml-cuda/common.cuh
View File

@@ -224,6 +224,11 @@ static const char * cu_get_error_str(CUresult err) {
#define AMD_MFMA_AVAILABLE
#endif // defined(GGML_USE_HIP) && defined(CDNA) && !defined(GGML_HIP_NO_MMQ_MFMA)
// The Volta instructions are in principle available on Turing or newer but they are effectively unusable:
#if !defined(GGML_USE_HIP) && __CUDA_ARCH__ == GGML_CUDA_CC_VOLTA
#define VOLTA_MMA_AVAILABLE
#endif // !defined(GGML_USE_HIP) && __CUDA_ARCH__ == GGML_CUDA_CC_VOLTA
#if !defined(GGML_USE_HIP) && __CUDA_ARCH__ >= GGML_CUDA_CC_TURING
#define TURING_MMA_AVAILABLE
#endif // !defined(GGML_USE_HIP) && __CUDA_ARCH__ >= GGML_CUDA_CC_TURING
@@ -278,7 +283,10 @@ static bool amd_mfma_available(const int cc) {
#endif //!defined(GGML_HIP_NO_MMQ_MFMA)
}
// Volta technically had FP16 tensor cores but they work very differently compared to Turing and later.
static bool volta_mma_available(const int cc) {
return GGML_CUDA_CC_IS_NVIDIA(cc) && ggml_cuda_highest_compiled_arch(cc) == GGML_CUDA_CC_VOLTA;
}
static bool turing_mma_available(const int cc) {
return GGML_CUDA_CC_IS_NVIDIA(cc) && ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_TURING;
}