oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 23:23:43 +00:00
Code Issues Projects Releases Packages Wiki Activity

llama.cpp: Use -1 instead of 0 for auto gpu_layers

Browse source
This commit is contained in:
oobabooga 2026-03-04 19:21:45 -08:00
parent d45aa6606a
commit fbfcd59fe0
4 changed files with 8 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/ui_model_menu.py
View file

@ -41,7 +41,7 @@ def create_ui():
gr.Markdown("## Main options")
with gr.Row():
with gr.Column():
shared.gradio['gpu_layers'] = gr.Slider(label="gpu-layers", minimum=0, maximum=get_initial_gpu_layers_max(), step=1, value=shared.args.gpu_layers, info='0 = auto (llama.cpp decides via --fit). Set manually to override.')
shared.gradio['gpu_layers'] = gr.Slider(label="gpu-layers", minimum=-1, maximum=get_initial_gpu_layers_max(), step=1, value=shared.args.gpu_layers, info='Number of layers to offload to the GPU. -1 = auto (llama.cpp decides via --fit).')
shared.gradio['ctx_size'] = gr.Slider(label='ctx-size', minimum=256, maximum=131072, step=256, value=shared.args.ctx_size, info='Context length. Common values: 4096, 8192, 16384, 32768, 65536, 131072.')
shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
shared.gradio['attn_implementation'] = gr.Dropdown(label="attn-implementation", choices=['sdpa', 'eager', 'flash_attention_2'], value=shared.args.attn_implementation, info='Attention implementation.')