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

AutoAWQ: initial support (#3999)

Browse source
This commit is contained in:
cal066 2023-10-05 16:19:18 +00:00 • committed by GitHub
parent 3f56151f03
commit cc632c3f33
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 75 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/ui_model_menu.py
View file

@ -99,7 +99,7 @@ def create_ui():
with gr.Column():
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
shared.gradio['no_inject_fused_attention'] = gr.Checkbox(label="no_inject_fused_attention", value=shared.args.no_inject_fused_attention, info='Disable fused attention. Fused attention improves inference performance but uses more VRAM. Disable if running low on VRAM.')
shared.gradio['no_inject_fused_attention'] = gr.Checkbox(label="no_inject_fused_attention", value=shared.args.no_inject_fused_attention, info='Disable fused attention. Fused attention improves inference performance but uses more VRAM. Fuses layers for AutoAWQ. Disable if running low on VRAM.')
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.')