Update app.py

app.py

@@ -21,7 +21,7 @@ torch.backends.cuda.matmul.allow_bf16_reduced_precision_reduction = False
 torch.backends.cuda.matmul.allow_fp16_reduced_precision_reduction = False
 torch.backends.cudnn.allow_tf32 = False
 torch.backends.cudnn.deterministic = False
-torch.backends.cudnn.benchmark = True
+torch.backends.cudnn.benchmark = False
 torch.set_float32_matmul_precision("highest")
 
 # --- Model and Tokenizer Configuration ---