root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-30 21:34:36 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update ggml-cuda.cu

Browse Source 
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2023-12-18 14:21:38 +02:00 committed by GitHub
parent 3c8d6b160b
commit 30338c5643
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml-cuda.cu
View File

@ -8419,8 +8419,8 @@ static void ggml_cuda_mul_mat_mat_batched_cublas(const ggml_tensor * src0, const
cu_compute_type = CUBLAS_COMPUTE_32F; cu_compute_type = CUBLAS_COMPUTE_32F;
cu_data_type = CUDA_R_32F; cu_data_type = CUDA_R_32F;
alpha = (const char *) &alpha_f32; alpha = &alpha_f32;
beta = (const char *) &beta_f32; beta = &beta_f32;
} }
GGML_ASSERT(ne12 % ne02 == 0); GGML_ASSERT(ne12 % ne02 == 0);