Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-23 09:59:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix compile warning (#7454)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-05-22 12:36:37 +03:00
parent 95fb0aefab
commit 9b3d833189
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml-cuda/fattn-tile-f32.cu
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) { 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) { if (Q->ne[1] <= 16) {
constexpr int cols_per_block = 16; constexpr int cols_per_block = 16;