From 37e2980e05bbfd6ef15f3cd05246551ff464e6d6 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 17 Sep 2023 08:27:11 -0700 Subject: [PATCH] Recommend mul_mat_q for llama.cpp --- 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 dcb8778f..f965d80e 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -111,7 +111,7 @@ def create_ui(): shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap) shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram) shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock) - shared.gradio['mul_mat_q'] = gr.Checkbox(label="mul_mat_q", value=shared.args.mul_mat_q) + shared.gradio['mul_mat_q'] = gr.Checkbox(label="mul_mat_q", value=shared.args.mul_mat_q, info='Recommended in most cases. Improves generation speed by 10-20%.') shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.') shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17') shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)