diff options
Diffstat (limited to 'common/common.h')
| -rw-r--r-- | common/common.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/common/common.h b/common/common.h index 1359e76a..f29be5b5 100644 --- a/common/common.h +++ b/common/common.h @@ -59,6 +59,7 @@ struct gpt_params { float p_split = 0.1f; // speculative decoding split probability int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default) int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-1 - use default) + llama_split_mode split_mode = LLAMA_SPLIT_LAYER; // how to split the model across GPUs int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs int32_t n_beams = 0; // if non-zero then use beam search of given width. |