mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add the --disable_exllama option for AutoGPTQ

Browse source
This commit is contained in:
Chris Lefever 2023-08-12 02:26:58 -04:00
parent 0e05818266
commit 0230fa4e9c
6 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/ui_model_menu.py
View file

@ -98,6 +98,7 @@ def create_ui():
shared.gradio['no_inject_fused_mlp'] = gr.Checkbox(label="no_inject_fused_mlp", value=shared.args.no_inject_fused_mlp, info='Affects Triton only. Disable fused MLP. Fused MLP improves performance but uses more VRAM. Disable if running low on VRAM.')
shared.gradio['no_use_cuda_fp16'] = gr.Checkbox(label="no_use_cuda_fp16", value=shared.args.no_use_cuda_fp16, info='This can make models faster on some systems.')
shared.gradio['desc_act'] = gr.Checkbox(label="desc_act", value=shared.args.desc_act, info='\'desc_act\', \'wbits\', and \'groupsize\' are used for old models without a quantize_config.json.')
shared.gradio['disable_exllama'] = gr.Checkbox(label="disable_exllama", value=shared.args.disable_exllama, info='Disable ExLlama kernel, which can improve inference speed on some systems.')
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)