From 249bd6eea2b7f07f73e96f5cfb32218196a9b237 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Thu, 5 Mar 2026 18:11:55 -0800 Subject: [PATCH] UI: Update the parallel info message --- modules/ui_model_menu.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py index 0c2450d5..e6e57a22 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -91,9 +91,9 @@ def create_ui(): with gr.Accordion("See more options", open=False, elem_classes='tgw-accordion'): with gr.Row(): with gr.Column(): + shared.gradio['parallel'] = gr.Slider(label="parallel", minimum=1, step=1, maximum=64, value=shared.args.parallel, info='Number of parallel request slots for the API. The context size is divided equally among slots. For example, to have 4 slots with 8192 context each, set ctx_size to 32768.') 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['parallel'] = gr.Slider(label="parallel", minimum=1, step=1, maximum=64, value=shared.args.parallel, info='Number of parallel request slots. The context size is divided equally among slots. For example, to have 4 slots with 8192 context each, set ctx_size to 32768.') 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')