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

CUDA GPU acceleration for LoRAs + f16 models (#1970)

Browse source
This commit is contained in:
Johannes Gäßler 2023-06-28 18:35:54 +02:00 • committed by GitHub
parent cfa0750bc9
commit 7f9753fa12
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 78 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml-cuda.h
View file

@ -29,6 +29,7 @@ void ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor);
void ggml_cuda_free_data(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
void ggml_cuda_set_main_device(int main_device);
void ggml_cuda_set_scratch_size(size_t scratch_size);
void ggml_cuda_free_scratch(void);