Add /health Endpoint for both Servers (#1540)

vllm/entrypoints/api_server.py

@@ -17,6 +17,12 @@ app = FastAPI()
 engine = None
 
 
+@app.get("/health")
+async def health() -> Response:
+    """Health check."""
+    return Response(status_code=200)
+
+
 @app.post("/generate")
 async def generate(request: Request) -> Response:
     """Generate completion for the request.

vllm/entrypoints/openai/api_server.py

@@ -13,7 +13,7 @@ import uvicorn
 from fastapi import Request
 from fastapi.exceptions import RequestValidationError
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import JSONResponse, StreamingResponse
+from fastapi.responses import JSONResponse, StreamingResponse, Response
 from packaging import version
 
 from vllm.engine.arg_utils import AsyncEngineArgs
@@ -145,6 +145,12 @@ async def check_length(
         return input_ids, None
 
 
+@app.get("/health")
+async def health() -> Response:
+    """Health check."""
+    return Response(status_code=200)
+
+
 @app.get("/v1/models")
 async def show_available_models():
     """Show available models. Right now we only have one model."""