From 3020f2e5ec823eef91475bcbcc929b1b2d9ca614 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Thu, 9 Jan 2025 12:44:03 -0800 Subject: [PATCH] UI: improve the info message about --tensorcores --- 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 eac0cba6..d5116938 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -103,7 +103,7 @@ def create_ui(): shared.gradio['num_experts_per_token'] = gr.Number(label="Number of experts per token", value=shared.args.num_experts_per_token, info='Only applies to MoE models like Mixtral.') with gr.Column(): - shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This may increase performance on newer cards.') + shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled without GGML_CUDA_FORCE_MMQ. This may improve performance on newer cards.') shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit) shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit) shared.gradio['torch_compile'] = gr.Checkbox(label="torch-compile", value=shared.args.torch_compile, info='Compile the model with torch.compile for improved performance.')