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

remove support chunking for paged

Browse Source
This commit is contained in:
OlivierDehaene 2024-10-11 15:19:14 +02:00
parent df98299919
commit 5e70158b2c
No known key found for this signature in database
GPG Key ID: BB104D67809DA93C
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -72,6 +72,12 @@ class Model(ABC):
"Prefill chunking will be turned off",
)
support_chunking = False
if ATTENTION not in ["flashinfer", "flashdecoding"] and support_chunking:
log_master(
logger.warning,
"Prefill chunking is only supported with `flashinfer` or `flashdecoding` attention types.",
)
support_chunking = False
self.support_chunking = support_chunking
set_support_chunking(support_chunking)