huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

dead code

Browse Source
This commit is contained in:
fxmarty 2024-06-07 12:38:56 +00:00
parent b884d2b9b8
commit fb5487d00c
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/__init__.py
View File

@ -50,8 +50,6 @@ __all__ = [
FLASH_ATT_ERROR_MESSAGE = "{} requires Flash Attention enabled models." FLASH_ATT_ERROR_MESSAGE = "{} requires Flash Attention enabled models."
SLIDING_WINDOW_MESSAGE = "The backend {} does not support sliding window attention. TGI webserver was started max_input_tokens={} larger than sliding_window={}. To use this model with the {} backend, please launch TGI with the argument `--max-batch-prefill-tokens` smaller than {}."
FLASH_ATTENTION = True FLASH_ATTENTION = True
try: try: