LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity

Compiler warning

Browse Source
This commit is contained in:
Kawrakow
2026-07-13 10:34:26 +00:00
parent 593a196f78
commit 7937465ff1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmq.cu
+1 -1
View File
@@ -146,7 +146,7 @@ void ggml_cuda_op_mul_mat_q(
ggml_backend_cuda_context & ctx,
const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,
const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, const int64_t row_high, const int64_t src1_ncols,
const int64_t src1_padded_row_size, cudaStream_t stream) {
const int64_t src1_padded_row_size, [[maybe_unused]] cudaStream_t stream) {
const int64_t ne00 = src0->ne[0];
const int64_t nb01 = ggml_row_size(src0->type, ne00);