From d0a4993cf483eaf0a4a4d96b5418c8da17dc23b4 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sat, 14 Mar 2026 09:53:12 -0700 Subject: [PATCH] UI: Increase ctx-size slider maximum to 1M and step to 1024 --- 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 d17f586b..6ab19b7c 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -42,7 +42,7 @@ def create_ui(): with gr.Row(): with gr.Column(): 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.') - shared.gradio['ctx_size'] = gr.Slider(label='ctx-size', minimum=0, maximum=262144, step=256, value=shared.args.ctx_size, info='Context length. llama.cpp: 0 = auto if gpu-layers is also -1. Common values: 4096, 8192, 16384, 32768, 65536, 131072.') + shared.gradio['ctx_size'] = gr.Slider(label='ctx-size', minimum=0, maximum=1048576, step=1024, value=shared.args.ctx_size, info='Context length. llama.cpp: 0 = auto if gpu-layers is also -1. 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.') shared.gradio['cache_type'] = gr.Dropdown(label="cache-type", choices=['fp16', 'q8_0', 'q4_0', 'fp8', 'q8', 'q7', 'q6', 'q5', 'q4', 'q3', 'q2'], value=shared.args.cache_type, allow_custom_value=True, info='Valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV3 - fp16, q2 to q8. For ExLlamaV3, you can type custom combinations for separate k/v bits (e.g. q4_q8).')