oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-05 06:35:15 +00:00
Code Issues Projects Releases Packages Wiki Activity

Add --no_xformers and --no_sdpa flags for ExllamaV2

Browse source
This commit is contained in:
oobabooga 2024-07-11 15:47:37 -07:00
parent 512b311137
commit e436d69e2b
6 changed files with 15 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/ui_model_menu.py
View file

@ -138,7 +138,9 @@ def create_ui():
shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
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['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn)
shared.gradio['no_xformers'] = gr.Checkbox(label="no_xformers", value=shared.args.no_xformers)
shared.gradio['no_sdpa'] = gr.Checkbox(label="no_sdpa", value=shared.args.no_sdpa)
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Necessary to use CFG with this loader.')
shared.gradio['cpp_runner'] = gr.Checkbox(label="cpp-runner", value=shared.args.cpp_runner, info='Enable inference with ModelRunnerCpp, which is faster than the default ModelRunner.')
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.')