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 14:21:22 +02:00 committed by GitHub
parent 18c67bdd84
commit 3c8d6b160b
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

@ -8404,8 +8404,8 @@ static void ggml_cuda_mul_mat_mat_batched_cublas(const ggml_tensor * src0, const
const float alpha_f32 = 1.0f; const float alpha_f32 = 1.0f;
const float beta_f32 = 0.0f; const float beta_f32 = 0.0f;
const char * alpha = (const char *) &alpha_f16; const void * alpha = &alpha_f16;
const char * beta = (const char *) &beta_f16; const void * beta = &beta_f16;
if (dst->op_params[0] == GGML_PREC_DEFAULT) { if (dst->op_params[0] == GGML_PREC_DEFAULT) {
dst_f16 = (half *) ggml_cuda_pool_malloc(ne * sizeof(half), &dst_as); dst_f16 = (half *) ggml_cuda_pool_malloc(ne * sizeof(half), &dst_as);