Update app.py

app.py

@@ -1,8 +1,6 @@
 from fastapi import FastAPI, HTTPException, Request
 from fastapi.responses import StreamingResponse
 from llama_cpp import Llama
-import time
-import os
 
 app = FastAPI()
 
@@ -16,7 +14,6 @@ def generate_output_stream(prompt):
             if chunk.get('choices') and chunk['choices'][0].get('text'):
                 text = chunk['choices'][0]['text']
                 yield f"{text}\n"
-                time.sleep(0.01)  # Adjust the delay if needed
         except StopIteration:
             break