apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[LLM] support multi node deploy (#2708)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* [LLM] support multi node deploy

* Update engine.py

* fix bugs

* fix

* [LLM] support multi node deploy

* [LLM] support multi node deploy

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
ltd0924
2025-07-06 10:33:51 +08:00
committed by GitHub
parent 04a8e1ef2b
commit 68b4755587
13 changed files with 157 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/entrypoints/openai/api_server.py
View File

@@ -120,8 +120,8 @@ async def lifespan(app: FastAPI):
args.mm_processor_kwargs, args.enable_mm,
args.reasoning_parser)
app.state.dynamic_load_weight = args.dynamic_load_weight
chat_handler = OpenAIServingChat(engine_client, pid)
completion_handler = OpenAIServingCompletion(engine_client, pid)
chat_handler = OpenAIServingChat(engine_client, pid, args.pod_ips)
completion_handler = OpenAIServingCompletion(engine_client, pid, args.pod_ips)
engine_client.create_zmq_client(model=pid, mode=zmq.PUSH)
engine_client.pid = pid
app.state.engine_client = engine_client