tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-01 15:09:32 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-28 09:26:43 +01:00
committed by GitHub
parent 05e6f5aad0
commit 9c42b1718c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -109,9 +109,9 @@ static constexpr __device__ int get_mmq_x_max_device() {
#if __CUDA_ARCH__ >= GGML_CUDA_CC_VOLTA
#ifdef GGML_CUDA_FORCE_MMQ
return MMQ_DP4A_MAX_BATCH_SIZE;
#else // GGML_CUDA_FORCE_MMQ
return 128;
#else // GGML_CUDA_FORCE_MMQ
return MMQ_DP4A_MAX_BATCH_SIZE;
#endif // GGML_CUDA_FORCE_MMQ
#else // __CUDA_ARCH__ >= GGML_CUDA_CC_VOLTA