apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] fix multinode deployment (#2977)

Browse Source
This commit is contained in:
ltd0924
2025-07-24 15:04:04 +08:00
committed by GitHub
parent 3792345c3a
commit f935d6f862
9 changed files with 71 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
fastdeploy/entrypoints/openai/api_server.py
View File

@@ -113,10 +113,11 @@ async def lifespan(app: FastAPI):
args.mm_processor_kwargs,
args.enable_mm,
args.reasoning_parser,
args.data_parallel_size
)
app.state.dynamic_load_weight = args.dynamic_load_weight
chat_handler = OpenAIServingChat(engine_client, pid, args.dist_init_ip)
completion_handler = OpenAIServingCompletion(engine_client, pid, args.dist_init_ip)
chat_handler = OpenAIServingChat(engine_client, pid, args.ips)
completion_handler = OpenAIServingCompletion(engine_client, pid, args.ips)
engine_client.create_zmq_client(model=pid, mode=zmq.PUSH)
engine_client.pid = pid
app.state.engine_client = engine_client