vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
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) {
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;