Update app.py

app.py

@@ -1,10 +1,14 @@
 import subprocess
 import sys
+import shlex
 import spaces
 
 # install packages for mamba
-    subprocess.run("pip install https://github.com/Dao-AILab/causal-conv1d/releases/download/v1.0.0/causal_conv1d-1.0.0+cu122torch2.2cxx11abiTRUE-cp310-cp310-linux_x86_64.whl".split())
-    subprocess.run("pip install https://github.com/state-spaces/mamba/releases/download/v1.0.1/mamba_ssm-1.0.1+cu122torch2.2cxx11abiTRUE-cp310-cp310-linux_x86_64.whl".split())
+def install():
+    subprocess.run(shlex.split("pip install https://github.com/Dao-AILab/causal-conv1d/releases/download/v1.0.0/causal_conv1d-1.0.0+cu122torch2.2cxx11abiTRUE-cp310-cp310-linux_x86_64.whl"))
+    subprocess.run(shlex.split("pip install https://github.com/state-spaces/mamba/releases/download/v1.0.1/mamba_ssm-1.0.1+cu122torch2.2cxx11abiTRUE-cp310-cp310-linux_x86_64.whl"))
+
+install()
 
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
@@ -44,7 +48,7 @@ model = AutoModelForCausalLM.from_pretrained(
 if device == "cuda":
     model = torch.compile(model)
 
-install()
+
 
 @spaces.GPU
 def stream_chat(