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

Add no_flash_attn option

Browse source
This commit is contained in:
oobabooga 2023-11-02 08:19:42 -07:00
parent aaf726dbfb
commit 77abd9b69b
4 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -117,6 +117,7 @@ parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (
parser.add_argument('--gpu-split', type=str, help='Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7.')
parser.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequence length.')
parser.add_argument('--cfg-cache', action='store_true', help='ExLlama_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader, but not necessary for CFG with base ExLlama.')
parser.add_argument('--no_flash_attn', action='store_true', help='Force flash-attention to not be used.')
# AutoGPTQ
parser.add_argument('--triton', action='store_true', help='Use triton.')