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

Update common/common.cpp (suggested by JohannesGaessler)

Browse source 
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Yui 2024-04-08 09:17:33 +02:00 • committed by GitHub
parent 2549662cde
commit 2325ec0550
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -1412,7 +1412,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
if (llama_supports_gpu_offload()) { if (llama_supports_gpu_offload()) {
printf(" -ngl N, --n-gpu-layers N\n"); printf(" -ngl N, --n-gpu-layers N\n");
printf(" number of layers to store in VRAM\n"); printf(" number of layers to store in VRAM\n");
printf(" set to 'auto' or 'a' to determine max automatically based on VRAM size\n"); printf(" set to 'auto' or 'a' to estimate max automatically based on VRAM size\n");
printf(" -ngld N, --n-gpu-layers-draft N\n"); printf(" -ngld N, --n-gpu-layers-draft N\n");
printf(" number of layers to store in VRAM for the draft model\n"); printf(" number of layers to store in VRAM for the draft model\n");
printf(" -sm SPLIT_MODE, --split-mode SPLIT_MODE\n"); printf(" -sm SPLIT_MODE, --split-mode SPLIT_MODE\n");