runtime error

Exit code: 1. Reason: PyTorch version: 2.9.1+cu128 Loading model: Qwen/Qwen-Image-Edit-2509... The model will be automatically sharded across all available GPUs (8x L40S). ❌ Error loading model: auto not supported. Supported strategies are: balanced, cuda /app/app.py:130: UserWarning: The parameters have been moved from the Blocks constructor to the launch() method in Gradio 6.0: css. Please pass these parameters to launch() instead. with gr.Blocks(css=css) as demo: Traceback (most recent call last): File "/app/app.py", line 222, in <module> demo.queue(concurrency_count=2).launch() TypeError: Blocks.queue() got an unexpected keyword argument 'concurrency_count'

Container logs: