feat(app): add direct execution support for local development (vllm-project#341)

Signed-off-by: liuhy <[email protected]>

Author: FeiDaLI

tools/mock-vllm/app.py

@@ -2,6 +2,7 @@
 import time
 from typing import List, Optional
 
+import uvicorn
 from fastapi import FastAPI
 from pydantic import BaseModel
 
@@ -79,3 +80,7 @@ def estimate_tokens(text: str) -> int:
         # Some SDKs look for token_usage; keep it as an alias for convenience.
         "token_usage": usage,
     }
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)