tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-11 11:05:39 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: app option to compile without FlashAttention (#12025)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-22 20:44:34 +01:00
committed by GitHub
parent 36c258ee92
commit a28e0d5eb1
13 changed files with 46 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -3203,7 +3203,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_FLASH_ATTN_EXT: {
#ifndef FLASH_ATTN_AVAILABLE
return false;
#endif
#endif // FLASH_ATTN_AVAILABLE
if (op->src[1]->type == GGML_TYPE_BF16 || op->src[2]->type == GGML_TYPE_BF16) {
return false;
}