upstream-archive/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-08-05 17:40:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

whisper : add note that ggml_mul_mat_pad does not work with CUDA

Browse Source
This commit is contained in:
Georgi Gerganov
2023-11-11 13:04:58 +02:00
parent 0867e696a7
commit b27726da93
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
whisper.cpp
View File

@@ -207,6 +207,7 @@ static struct ggml_tensor * ggml_mul_mat_pad(struct ggml_context * ctx, struct g
}
// TODO: check if other platforms can benefit from this optimization
// TODO: CUDA is currently broken - seems ggml_mul_mat does not handle views correctly
#if defined(GGML_USE_METAL)
#define ggml_mul_mat ggml_mul_mat_pad
#endif