tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 12:19:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

musa: fix failures in test-backend-ops for mul_mat_id op (#15236)

Browse Source 
* musa: fix failures in test-backend-ops for mul_mat_id op

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
2025-08-12 10:02:51 +08:00
committed by GitHub
parent be48528b06
commit 25ff6f7659
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/common.cuh
View File

@@ -312,11 +312,11 @@ static bool turing_mma_available(const int cc) {
}
static bool ampere_mma_available(const int cc) {
return cc < GGML_CUDA_CC_OFFSET_AMD && ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_AMPERE;
return GGML_CUDA_CC_IS_NVIDIA(cc) && ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_AMPERE;
}
static bool cp_async_available(const int cc) {
return cc < GGML_CUDA_CC_OFFSET_AMD && ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_AMPERE;
return GGML_CUDA_CC_IS_NVIDIA(cc) && ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_AMPERE;
}
static constexpr __device__ int ggml_cuda_get_physical_warp_size() {