Update app.py

app.py

@@ -1,11 +1,13 @@
-!CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --upgrade --force-reinstall llama-cpp-python --no-cache-dir
-
+import subprocess
 from threading import Thread
 from llama_cpp import Llama
 import torch
 import gradio as gr
 import re
 
+subprocess.call(f"""CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --upgrade --force-reinstall llama-cpp-python --no-cache-dir
+""", shell=True)
+
 torch_device = "cuda" if torch.cuda.is_available() else "cpu"
 print("Running on device:", torch_device)
 print("CPU threads:", torch.get_num_threads())