Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

CUDA: fix crash on uneven context without FA (#16988)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-11-06 14:05:47 +01:00
committed by GitHub
parent 5b180c3d60
commit aa374175c3
7 changed files with 44 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmf.cuh
+1 -1
View File
@@ -17,7 +17,7 @@ struct mmf_ids_data {
void ggml_cuda_mul_mat_f(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * ids, ggml_tensor * dst);
bool ggml_cuda_should_use_mmf(enum ggml_type type, int cc, int warp_size, const int64_t * scr0_ne, const int src1_ncols, bool mul_mat_id);
bool ggml_cuda_should_use_mmf(enum ggml_type type, int cc, int warp_size, const int64_t * scr0_ne, const size_t * src0_nb, const int src1_ncols, bool mul_mat_id);
template <typename T, int rows_per_block, int cols_per_block, int nwarps, bool has_ids>
__launch_bounds__(ggml_cuda_get_physical_warp_size()*nwarps, 1)