From 5c89068168e6a5e65d55832e7a725f4688bc9434 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Wed, 8 Jan 2025 17:36:30 -0800 Subject: [PATCH] UI: add an info message for the new Static KV cache option --- modules/ui_parameters.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/ui_parameters.py b/modules/ui_parameters.py index f22f6233..c8fd6bc7 100644 --- a/modules/ui_parameters.py +++ b/modules/ui_parameters.py @@ -83,7 +83,7 @@ def create_ui(default_preset): shared.gradio['add_bos_token'] = gr.Checkbox(value=shared.settings['add_bos_token'], label='Add the bos_token to the beginning of prompts', info='Disabling this can make the replies more creative.') shared.gradio['skip_special_tokens'] = gr.Checkbox(value=shared.settings['skip_special_tokens'], label='Skip special tokens', info='Some specific models need this unset.') shared.gradio['stream'] = gr.Checkbox(value=shared.settings['stream'], label='Activate text streaming') - shared.gradio['static_cache'] = gr.Checkbox(value=shared.settings['static_cache'], label='Static KV cache') + shared.gradio['static_cache'] = gr.Checkbox(value=shared.settings['static_cache'], label='Static KV cache', info='Use a static cache for improved performance.') with gr.Column(): shared.gradio['truncation_length'] = gr.Number(precision=0, step=256, value=get_truncation_length(), label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')