Update app.py

app.py

@@ -143,12 +143,13 @@ theme = gr.themes.Monochrome(
     ],
 )
 
-@spaces.GPU
+
 def stream(model, code, generate_kwargs):
     input_ids = tokenizer(code, return_tensors="pt").to("cuda")
     generated_ids = model.generate(**input_ids, **generate_kwargs)
     return tokenizer.decode(generated_ids[0][input_ids["input_ids"].shape[1]:], skip_special_tokens=True).strip()
 
+@spaces.GPU(enable_queue=True)
 def generate(
     prompt, temperature=0.6, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, library="LangChain", method="Prefix"
 ):