apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BUGFIX] fix ep mixed bug (#3513)

Browse Source 
* Update expert_service.py

* Update engine.py

* Update engine.py

* Update engine.py

* Update expert_service.py

* Update engine.py
This commit is contained in:
ltd0924
2025-08-22 11:35:50 +08:00
committed by GitHub
parent 4a9c04a746
commit c18975366e
2 changed files with 15 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
fastdeploy/engine/engine.py
View File

@@ -124,8 +124,9 @@ class LLMEngine:
cfg.max_num_seqs, cfg, cfg.tensor_parallel_size, cfg.splitwise_role
)
os.environ["INFERENCE_MSG_QUEUE_ID"] = str(self.cfg.engine_worker_queue_port)
os.environ["INFERENCE_MSG_QUEUE_ID"] = str(
self.cfg.engine_worker_queue_port + self.cfg.worker_num_per_node * self.cfg.node_rank
)
self.split_connector = SplitwiseConnector(cfg, self.scheduler, self.engine_worker_queue, self.resource_manager)
self.token_processor = TokenProcessor(