Update app.py

app.py

@@ -9,7 +9,7 @@ model = Llama.from_pretrained(
     repo_id="unsloth/Qwen3.5-35B-A3B-GGUF",
     filename="Qwen3.5-35B-A3B-UD-IQ4_XS.gguf",
     n_ctx=2048,
-    n_threads=2,
+    n_threads=8,
 )
 
 def get_stats():
@@ -22,9 +22,6 @@ def get_stats():
 
 def chat(message, history):
     messages = [{"role": "system", "content": "Reply directly without any reasoning or thinking process."}]
-    for user, assistant in history:
-        messages.append({"role": "user", "content": user})
-        messages.append({"role": "assistant", "content": assistant})
     messages.append({"role": "user", "content": message})
 
     output = ""