apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Enable prefix caching as default (#3816)

Browse Source 
* [Feature] Enable prefix caching as default

* [Feature] Enable prefix caching as default

* Set prefix caching as default

* skip dynamic load

* fix kill bug

* fix kill bug

* fix kill bug

* fix ci

* fix

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
chenjian
2025-09-06 09:51:34 +08:00
committed by GitHub
parent 11b18e5ef0
commit 41cd3e24c9
6 changed files with 37 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/engine/engine.py
View File

@@ -342,7 +342,8 @@ class LLMEngine:
for p in self.cache_manager_processes:
llm_logger.info(f"Killing cache manager process {p.pid}")
try:
os.killpg(p.pid, signal.SIGTERM)
pgid = os.getpgid(p.pid)
os.killpg(pgid, signal.SIGTERM)
except Exception as e:
console_logger.error(
f"Error killing cache manager process {p.pid}: {e}, {str(traceback.format_exc())}"