happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix CI

This commit is contained in:
bssrdf 2025-11-19 07:47:11 -05:00
parent 73444564e6
commit e760cd49bd
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/conv2d-implicit.cu
View File

@ -871,10 +871,13 @@ static __global__ void conv2d_implicit_kernel(const half * __restrict__ input,
prepareIteratorA<BM, BK, A_K_STRID, ROW_STEP>(thread_row, masks_a, element_offset_a, param);
#ifdef CP_ASYNC_AVAILABLE
unsigned int iter_src_idx = thread_row * param.weightKOffset;
unsigned int iter_dst_idx = thread_row * TILE_COLS_VECTORIZED + thread_col;
unsigned int krow_idx = thread_row + blockIdx.x * BN;
const int ITER_SRC_STEPS = ROW_STEP * param.weightKOffset;
#endif
// prefetch the first block tile of A,B into shared memory