apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] fix create_cache_tensor for ep (#4542)

Browse Source 
* [fix] fix create_cache_tensor for ep

* [fix] fix again
This commit is contained in:
李泳桦
2025-10-24 11:31:13 +08:00
committed by GitHub
parent f7069b8057
commit 8edc5cca91
2 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/engine.py
View File

@@ -119,7 +119,7 @@ class LLMEngine:
# If block numer is specified and model is deployed in mixed mode, start cache manager first
if not self.do_profile and self.cfg.scheduler_config.splitwise_role != "mixed":
device_ids = self.cfg.parallel_config.device_ids.split(",")
self.cache_manager_processes = self.engine.start_cache_service(device_ids, self.ipc_signal_suffix, True)
self.cache_manager_processes = self.engine.start_cache_service(device_ids, self.ipc_signal_suffix)
# Start workers
self.worker_proc = self._start_worker_service()