simcop2387/text-generation-webui-mirror
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-06-07 14:17:09 -04:00
Code Issues Projects Releases Packages Wiki Activity

Rename --n-gpu-layers to --gpu-layers

Browse source
This commit is contained in:
oobabooga 2025-05-04 20:03:55 -07:00
parent d0211afb3c
commit df7bb0db1f
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -120,7 +120,7 @@ group.add_argument('--threads-batch', type=int, default=0, help='Number of threa
group.add_argument('--batch-size', type=int, default=256, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
group.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
group.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
group.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
group.add_argument('--gpu-layers', '--n-gpu-layers', type=int, default=0, metavar='N', help='Number of layers to offload to the GPU.')
group.add_argument('--tensor-split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.')
group.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
group.add_argument('--no-kv-offload', action='store_true', help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')

2
modules/ui_model_menu.py
View file

@ -49,7 +49,7 @@ def create_ui():
with gr.Blocks():
with gr.Row():
with gr.Column():
shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=256, value=shared.args.n_gpu_layers, info='Must be greater than 0 for the GPU to be used. ⚠️ Lower this value if you can\'t load the model.')
shared.gradio['n_gpu_layers'] = gr.Slider(label="gpu-layers", minimum=0, maximum=256, value=shared.args.n_gpu_layers, info='Must be greater than 0 for the GPU to be used. ⚠️ Lower this value if you can\'t load the model.')
shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=256, value=shared.args.threads)
shared.gradio['threads_batch'] = gr.Slider(label="threads_batch", minimum=0, step=1, maximum=256, value=shared.args.threads_batch)
shared.gradio['batch_size'] = gr.Slider(label="batch_size", minimum=1, maximum=4096, step=1, value=shared.args.batch_size)