tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 13:40:55 -04:00
Code Issues Packages Projects Releases Wiki Activity

common : restore --n-gpu-layers (#9371)

Browse Source
This commit is contained in:
slaren
2024-09-08 16:44:42 +02:00
committed by GitHub
parent 19f4a7b296
commit a249843d89
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(
{"-ngl", "--gpu-layers"}, "N",
{"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
"number of layers to store in VRAM",
[](gpt_params & params, int 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"));
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",
[](gpt_params & params, int value) {
params.n_gpu_layers_draft = value;