huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix prefix_caching variable, remove defaults in server (confusing a lot

Browse Source 
of the times).
This commit is contained in:
Nicolas Patry 2024-10-16 10:46:03 +02:00
parent 594a2b4a3d
commit 5c72f269b6
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/models/globals.py
View File

@ -5,9 +5,9 @@ from typing import Dict, Optional
from text_generation_server.utils.log import log_master from text_generation_server.utils.log import log_master
ATTENTION = os.getenv("ATTENTION", "flashinfer") ATTENTION = os.environ["ATTENTION"]
default_prefix_caching = "1" if ATTENTION in {"flashinfer", "flashdecoding"} else "0" # default_prefix_caching = "1" if ATTENTION in {"flashinfer", "flashdecoding"} else "0"
PREFIX_CACHING = os.getenv("PREFIX_CACHING", default_prefix_caching).lower() in { PREFIX_CACHING = os.environ["PREFIX_CACHING"].lower() in {
"1", "1",
"true", "true",
} }