Update app.py

app.py

@@ -5,6 +5,8 @@ import torch
 import optimum
 from transformers import (AutoModelForCausalLM, AutoTokenizer, LlamaForCausalLM, LlamaTokenizer, GenerationConfig, pipeline,)
 
+app = FastAPI()
+
 if torch.cuda.is_available():
     print("CUDA is available. GPU will be used.")
 else:
@@ -128,15 +130,5 @@ def generate_response(prompt: str) -> str:
     return generated_text
 
 
-app = FastAPI()
-
-
-# Run the FastAPI app
-async def run_app():
-    await uvicorn.run(app, host="0.0.0.0", port=8000)
-
 
-if __name__ == '__main__':
-    import asyncio
 
-    asyncio.run(run_app())