oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 15:13:38 +00:00
Code Issues Projects Releases Packages Wiki Activity

llama.cpp: Support literal flags in --extra-flags (e.g. --rpc, --jinja)

Browse source 
The old format is still accepted for backwards compatibility.
This commit is contained in:
oobabooga 2026-03-17 19:47:55 -07:00
parent 2a6b1fdcba
commit 7e54e7b7ae
3 changed files with 23 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/ui_model_menu.py
View file

@ -98,7 +98,7 @@ def create_ui():
shared.gradio['batch_size'] = gr.Slider(label="batch_size", minimum=1, maximum=4096, step=1, value=shared.args.batch_size)
shared.gradio['ubatch_size'] = gr.Slider(label="ubatch_size", minimum=1, maximum=4096, step=1, value=shared.args.ubatch_size)
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='List of proportions to split the model across multiple GPUs. Example: 60,40')
shared.gradio['extra_flags'] = gr.Textbox(label='extra-flags', info='Additional flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"', value=shared.args.extra_flags)
shared.gradio['extra_flags'] = gr.Textbox(label='extra-flags', info='Extra flags to pass to llama-server. Example: --jinja --rpc 192.168.1.100:50052', value=shared.args.extra_flags)
shared.gradio['cpu_memory'] = gr.Number(label="Maximum CPU memory in GiB. Use this for CPU offloading.", value=shared.args.cpu_memory)
shared.gradio['compute_dtype'] = gr.Dropdown(label="compute_dtype", choices=["bfloat16", "float16", "float32"], value=shared.args.compute_dtype, info='Used by load-in-4bit.')
shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type, info='Used by load-in-4bit.')