runtime error

es/gradio_client/utils.py", line 855, in synchronize_async return fsspec.asyn.sync(fsspec.asyn.get_loop(), func, *args, **kwargs) # type: ignore File "/usr/local/lib/python3.10/site-packages/fsspec/asyn.py", line 103, in sync raise return_result File "/usr/local/lib/python3.10/site-packages/fsspec/asyn.py", line 56, in _runner result[0] = await coro File "/usr/local/lib/python3.10/site-packages/gradio/helpers.py", line 487, in cache prediction = await Context.root_block.process_api( File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1928, in process_api result = await self.call_function( File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1514, in call_function prediction = await anyio.to_thread.run_sync( File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 859, in run result = context.run(func, *args) File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 833, in wrapper response = f(*args, **kwargs) File "/home/user/app/app.py", line 8, in func model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint, load_in_8bit=False) File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3279, in from_pretrained hf_*********.validate_environment( File "/usr/local/lib/python3.10/site-packages/transformers/quantizers/quantizer_bnb_8bit.py", line 62, in validate_environment raise RuntimeError("No GPU found. A GPU is needed for quantization.") RuntimeError: No GPU found. A GPU is needed for quantization.

Container logs: