xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-28 09:17:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1] Allow sliding window + prefix caching (#13069)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-03-12 11:21:19 -07:00 committed by GitHub
parent f5d3acd474
commit 53be4a8634
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config.py
View File

@ -1146,7 +1146,7 @@ class CacheConfig:
if not self.enable_prefix_caching:
return
if self.sliding_window is not None:
if self.sliding_window is not None and not envs.VLLM_USE_V1:
raise NotImplementedError(
"Prefix caching is not supported with sliding window. "
"Run with --disable-sliding-window to use prefix caching.")