public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-03 04:51:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix compile warning (llama/7454)

Browse Source
This commit is contained in:
Georgi Gerganov
2024-06-16 18:19:48 +03:00
parent 29ab5d0326
commit 5848dfd9c8
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml-cuda/fattn-tile-f32.cu
+1 -2
View File
@@ -283,8 +283,7 @@ void launch_fattn_tile_f32_64_128(ggml_backend_cuda_context & ctx, ggml_tensor *
}
void ggml_cuda_flash_attn_ext_tile_f32(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const ggml_tensor * KQV = dst;
const ggml_tensor * Q = dst->src[0];
const ggml_tensor * Q = dst->src[0];
if (Q->ne[1] <= 16) {
constexpr int cols_per_block = 16;