From e79e7b90dceef9c698c82a2b15e30b0fe454eb54 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Thu, 4 Jul 2024 20:21:28 -0700 Subject: [PATCH] UI: Move the cache_8bit and cache_4bit elements up --- modules/ui_model_menu.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py index 9a4e7351..4659c6a8 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -120,6 +120,8 @@ def create_ui(): shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices) shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards.') shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming_llm", value=shared.args.streaming_llm, info='(experimental) Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.') + shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.') + shared.gradio['cache_4bit'] = gr.Checkbox(label="cache_4bit", value=shared.args.cache_4bit, info='Use Q4 cache to save VRAM.') shared.gradio['attention_sink_size'] = gr.Number(label="attention_sink_size", value=shared.args.attention_sink_size, precision=0, info='StreamingLLM: number of sink tokens. Only used if the trimmed prompt doesn\'t share a prefix with the old prompt.') shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu, info='llama.cpp: Use llama-cpp-python compiled without GPU acceleration. Transformers: use PyTorch in CPU mode.') shared.gradio['row_split'] = gr.Checkbox(label="row_split", value=shared.args.row_split, info='Split the model by rows across GPUs. This may improve multi-gpu performance.') @@ -135,8 +137,6 @@ def create_ui(): shared.gradio['numa'] = gr.Checkbox(label="numa", value=shared.args.numa, info='NUMA support can help on some systems with non-uniform memory access.') shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk) shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16) - shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.') - shared.gradio['cache_4bit'] = gr.Checkbox(label="cache_4bit", value=shared.args.cache_4bit, info='Use Q4 cache to save VRAM.') shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.') shared.gradio['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn, info='Force flash-attention to not be used.') shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Necessary to use CFG with this loader.')