diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/llama.h b/include/llama.h index f1511548..0f3ae862 100644 --- a/include/llama.h +++ b/include/llama.h @@ -325,6 +325,7 @@ extern "C" { struct llama_model_params { int32_t n_gpu_layers; // number of layers to store in VRAM + int32_t mla; // MLA implementation to use (only applicable to DeepSeek models at this point) enum llama_split_mode split_mode; // how to split the model across multiple GPUs // main_gpu interpretation depends on split_mode: |