oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-09 08:33:41 +00:00
Code Issues Projects Releases Packages Wiki Activity

Transformers loader: replace use_flash_attention_2/use_eager_attention with a unified attn_implementation

Browse source 
Closes #7107
This commit is contained in:
oobabooga 2025-07-09 18:38:45 -07:00
parent 511bb31646
commit 6c2bdda0f0
6 changed files with 5 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

3
modules/shared.py
View file

@ -61,8 +61,7 @@ group.add_argument('--no-cache', action='store_true', help='Set use_cache to Fal
group.add_argument('--trust-remote-code', action='store_true', help='Set trust_remote_code=True while loading the model. Necessary for some models.')
group.add_argument('--force-safetensors', action='store_true', help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.')
group.add_argument('--no_use_fast', action='store_true', help='Set use_fast=False while loading the tokenizer (it\'s True by default). Use this if you have any problems related to use_fast.')
group.add_argument('--use_flash_attention_2', action='store_true', help='Set use_flash_attention_2=True while loading the model.')
group.add_argument('--use_eager_attention', action='store_true', help='Set attn_implementation= eager while loading the model.')
group.add_argument('--attn-implementation', type=str, default='sdpa', help='Attention implementation. Valid options: sdpa, eager, flash_attention_2.')
group.add_argument('--torch-compile', action='store_true', help='Compile the model with torch.compile for improved performance.')
# bitsandbytes 4-bit