ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

musa: refine compute capability (#12493)

Browse source 
* musa: refine compute capability

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Address review comments

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2025-03-22 17:11:37 +08:00 • committed by GitHub
parent eddfb43850
commit fac63a3d78
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 44 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn.cu
View file

@ -253,7 +253,7 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
const int warp_size = ggml_cuda_info().devices[ggml_cuda_get_device()].warp_size;
const enum ggml_prec prec = ggml_flash_attn_ext_get_prec(KQV);
if (cc >= GGML_CUDA_CC_OFFSET_AMD) {
if (GGML_CUDA_CC_IS_AMD(cc)) {
#if defined(GGML_HIP_ROCWMMA_FATTN)
if (fp16_mma_available(cc)) {
ggml_cuda_flash_attn_ext_wmma_f16(ctx, dst);