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

common : restore --n-gpu-layers

Browse source
This commit is contained in:
slaren 2024-09-08 15:07:46 +02:00
parent 2a358fb0c4
commit 80f6666b26
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -1656,7 +1656,7 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
} }
)); ));
add_opt(llama_arg( add_opt(llama_arg(
{"-ngl", "--gpu-layers"}, "N", {"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
"number of layers to store in VRAM", "number of layers to store in VRAM",
[](gpt_params & params, int value) { [](gpt_params & params, int value) {
params.n_gpu_layers = value; params.n_gpu_layers = value;
@ -1667,7 +1667,7 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
} }
).set_env("LLAMA_ARG_N_GPU_LAYERS")); ).set_env("LLAMA_ARG_N_GPU_LAYERS"));
add_opt(llama_arg( add_opt(llama_arg(
{"-ngld", "--gpu-layers-draft"}, "N", {"-ngld", "--gpu-layers-draft", "--n-gpu-layers-draft"}, "N",
"number of layers to store in VRAM for the draft model", "number of layers to store in VRAM for the draft model",
[](gpt_params & params, int value) { [](gpt_params & params, int value) {
params.n_gpu_layers_draft = value; params.n_gpu_layers_draft = value;