diff options
| author | Johannes Gäßler <johannesg@5d6.de> | 2023-06-28 18:35:54 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-28 18:35:54 +0200 |
| commit | 7f9753fa1263c4eded9a3de19778562f0e1093d7 (patch) | |
| tree | d003fd220c810884cf93ed17d0f4ae518d0bf3e2 /ggml-cuda.h | |
| parent | cfa0750bc9dbc2d957a91b8ed09ab0035d8f3d4e (diff) | |
CUDA GPU acceleration for LoRAs + f16 models (#1970)
Diffstat (limited to 'ggml-cuda.h')
| -rw-r--r-- | ggml-cuda.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-cuda.h b/ggml-cuda.h index d32b448..7a65a35 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -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); |