fix: make model name and port configurable via environment variables

vllm/server.py

@@ -29,7 +29,7 @@ app = FastAPI(title="Simple vLLM Server", version="1.0.0")
 
 # Global engine instance
 engine: Optional[AsyncLLMEngine] = None
-model_name: str = "Qwen/Qwen2.5-7B-Instruct"
+model_name: str = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-7B-Instruct")
 
 # Request/Response models
 class CompletionRequest(BaseModel):
@@ -294,7 +294,7 @@ if __name__ == "__main__":
 
     # Get configuration from environment
     host = os.getenv("VLLM_HOST", "0.0.0.0")
-    port = int(os.getenv("VLLM_PORT", "8000"))
+    port = int(os.getenv("PORT", os.getenv("VLLM_PORT", "8000")))
 
     logger.info(f"Starting vLLM server on {host}:{port}")