EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

CUDA: Fix clang warnings (#12540)

Browse Source 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR
2025-03-24 18:28:34 +08:00
committed by GitHub
parent c54f6b7988
commit 7ea75035b6
4 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -27,8 +27,8 @@ void ggml_cuda_op_mul_mat_q(
// The stream-k decomposition is only faster for recent NVIDIA GPUs.
// Also its fixup needs to allocate a temporary buffer in the memory pool.
// There are multiple parallel CUDA streams for src1_ncols != ne11 which would introduce a race condition for this buffer.
const bool use_stream_k = ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_VOLTA &&
GGML_CUDA_CC_IS_NVIDIA(cc) && src1_ncols == ne11;
const bool use_stream_k = GGML_CUDA_CC_IS_NVIDIA(cc) &&
ggml_cuda_highest_compiled_arch(cc) >= GGML_CUDA_CC_VOLTA && src1_ncols == ne11;
const mmq_args args = {src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stride00, src1_padded_row_size, src1_ncols, ne11, nrows_dst, use_stream_k};
switch (src0->type) {