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

fix whitespace

Browse source
This commit is contained in:
slaren 2024-01-11 03:28:07 +01:00
parent d83c084020
commit 6dcc42bd6b
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama.h
View file

@ -185,12 +185,13 @@ extern "C" {
struct llama_model_params { struct llama_model_params {
int32_t n_gpu_layers; // number of layers to store in VRAM int32_t n_gpu_layers; // number of layers to store in VRAM
enum llama_split_mode split_mode; // how to split the model across multiple GPUs enum llama_split_mode split_mode; // how to split the model across multiple GPUs
// main_gpu interpretation depends on split_mode: // main_gpu interpretation depends on split_mode:
// LLAMA_SPLIT_NONE: the GPU that is used for the entire model // LLAMA_SPLIT_NONE: the GPU that is used for the entire model
// LLAMA_SPLIT_ROW: the GPU that is used for small tensors and intermediate results // LLAMA_SPLIT_ROW: the GPU that is used for small tensors and intermediate results
// LLAMA_SPLIT_LAYER: ignored // LLAMA_SPLIT_LAYER: ignored
int32_t main_gpu; int32_t main_gpu;
// proportion of the model (layers or rows) to offload to each GPU, size: LLAMA_MAX_DEVICES // proportion of the model (layers or rows) to offload to each GPU, size: LLAMA_MAX_DEVICES
const float * tensor_split; const float * tensor_split;