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

Fix cuda warning

Browse source 
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
This commit is contained in:
Molly Sophia 2024-12-28 19:24:17 +08:00
parent 00930e6fe5
commit 08cf56060b
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml/src/ggml-cuda/gla.cu
View file

@ -73,7 +73,8 @@ void ggml_cuda_op_gated_linear_attn(ggml_backend_cuda_context & ctx, ggml_tensor
const int64_t C = dst->ne[0];
const int64_t H = dst->src[0]->ne[1];
const float scale = ((const float*)(dst->op_params))[0];
float scale;
memcpy(&scale, (float*)dst->op_params, sizeof(float));
float * dst_d = (float *)dst->data;