Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-29 21:50:16 +01:00
Code Issues Packages Projects Releases Wiki Activity

Simplify the warning when flash-attn fails to import

Browse Source
This commit is contained in:
oobabooga 2024-09-28 20:33:17 -07:00
parent b92d7fd43e
commit c61b29b9ce
2 changed files with 0 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
modules/exllamav2.py
View File

@ -19,14 +19,6 @@ from modules.text_generation import get_max_prompt_length
try:
import flash_attn
except ModuleNotFoundError:
logger.warning(
'You are running ExLlamaV2 without flash-attention. This will cause the VRAM usage '
'to be a lot higher than it could be.\n'
'Try installing flash-attention following the instructions here: '
'https://github.com/Dao-AILab/flash-attention#installation-and-features'
)
pass
except Exception:
logger.warning('Failed to load flash-attention due to the following error:\n')
traceback.print_exc()

8
modules/exllamav2_hf.py
View File

@ -21,14 +21,6 @@ from modules.logging_colors import logger
try:
import flash_attn
except ModuleNotFoundError:
logger.warning(
'You are running ExLlamaV2 without flash-attention. This will cause the VRAM usage '
'to be a lot higher than it could be.\n'
'Try installing flash-attention following the instructions here: '
'https://github.com/Dao-AILab/flash-attention#installation-and-features'
)
pass
except Exception:
logger.warning('Failed to load flash-attention due to the following error:\n')
traceback.print_exc()