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: 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

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

@@ -1192,7 +1192,7 @@ static void ggml_cuda_op_mul_mat_cublas(
const bool use_fp16 = (src0->type == GGML_TYPE_F16 || ggml_is_quantized(src0->type)) && ggml_is_contiguous(src0) && row_diff == src0->ne[1] && dst->op_params[0] == GGML_PREC_DEFAULT;
if (((cc >= GGML_CUDA_CC_VOLTA && GGML_CUDA_CC_IS_NVIDIA(cc)) || GGML_CUDA_CC_IS_AMD(cc)) && use_fp16) {
if (((GGML_CUDA_CC_IS_NVIDIA(cc) && cc >= GGML_CUDA_CC_VOLTA) || GGML_CUDA_CC_IS_AMD(cc)) && use_fp16) {
// convert src0 and src1 to fp16, multiply as fp16, convert dst to fp32
ggml_cuda_pool_alloc<half> src0_as_f16(ctx.pool(id));
if (src0->type != GGML_TYPE_F16) {