tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 05:25:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

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
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);