Update app.py

app.py

@@ -136,7 +136,7 @@ _model.eval()
 print("Generator ready.")
 
 # ── GPU-decorated inference ────────────────────────────────────────────────────
-@spaces.GPU(duration=240)
+@spaces.GPU
 def generate_candidates(query: str, passage_texts: list) -> list:
     """Runs inside real ZeroGPU GPU context."""
     results = []
@@ -340,4 +340,4 @@ Aravind Kashyap | PES2PGE24DS068 | Guide: Shankar DK | PES University
 *Asai et al., ICLR 2024 — SELF-RAG: Learning to Retrieve, Generate and Critique*
 """)
 
-demo.launch()
+demo.queue(default_concurrency_limit=1).launch()