A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 12:15 UTC
[Bugfix] Fix AttributeError: 'State' object has no attribute 'engine_client' (#17434)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Apr 30, 2025 at 15:11 UTC
be633fba0f8fc41b19a774a89ad055e54865af53
1 file changed
+1
-1
vllm/entrypoints/api_server.py
+1
-1
@@ -111,7 +111,7 @@ async def init_app(
111
engine = (llm_engine
112
if llm_engine is not None else AsyncLLMEngine.from_engine_args(
113
engine_args, usage_context=UsageContext.API_SERVER))
114
-
114
+ app.state.engine_client = engine
115
return app
116
117