runtime error

serve(sockets=sockets)) File "/usr/local/lib/python3.9/asyncio/runners.py", line 44, in run return loop.run_until_complete(main) File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete File "/home/user/.local/lib/python3.9/site-packages/uvicorn/server.py", line 69, in serve await self._serve(sockets) File "/home/user/.local/lib/python3.9/site-packages/uvicorn/server.py", line 76, in _serve config.load() File "/home/user/.local/lib/python3.9/site-packages/uvicorn/config.py", line 434, in load self.loaded_app = import_from_string(self.app) File "/home/user/.local/lib/python3.9/site-packages/uvicorn/importer.py", line 19, in import_from_string module = importlib.import_module(module_str) File "/usr/local/lib/python3.9/importlib/__init__.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "<frozen importlib._bootstrap>", line 1030, in _gcd_import File "<frozen importlib._bootstrap>", line 1007, in _find_and_load File "<frozen importlib._bootstrap>", line 986, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 680, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 850, in exec_module File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed File "/app/main.py", line 13, in <module> model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=hf_token) File "/home/user/.local/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained return model_class.from_pretrained( File "/home/user/.local/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3279, in from_pretrained hf_*********.validate_environment( File "/home/user/.local/lib/python3.9/site-packages/transformers/quantizers/quantizer_bnb_4bit.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: