AssertionError: Torch not compiled with CUDA enabled

(base) jetson@SSD:~/FastChat/FastChat$ python3 -m fastchat.serve.cli --model-path lmsys/fastchat-t5-3b-v1.0
You are using the legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This means that tokens that come after special tokens will not be properly handled. We recommend you to read the related pull request available at https://github.com/huggingface/transformers/pull/24565
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "/home/jetson/FastChat/FastChat/fastchat/serve/cli.py", line 280, in
main(args)
File "/home/jetson/FastChat/FastChat/fastchat/serve/cli.py", line 206, in main
chat_loop(
File "/home/jetson/FastChat/FastChat/fastchat/serve/inference.py", line 307, in chat_loop
model, tokenizer = load_model(
^^^^^^^^^^^
File "/home/jetson/FastChat/FastChat/fastchat/model/model_adapter.py", line 291, in load_model
model.to(device)
File "/home/jetson/miniconda3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 1900, in to
return super().to(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jetson/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1145, in to
return self._apply(convert)
^^^^^^^^^^^^^^^^^^^^
File "/home/jetson/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/home/jetson/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 820, in _apply
param_applied = fn(param)
^^^^^^^^^
File "/home/jetson/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1143, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jetson/miniconda3/lib/python3.11/site-packages/torch/cuda/init.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

Start with the reported command and traceback, then inspect fastchat/serve/cli.py, fastchat/serve/inference.py, and fastchat/model/model_adapter.py around device selection and model.to(device). Reproduce the failure in the reported environment and determine the supported device configuration. Done should mean the cause is resolved or the CLI gives a clear response when CUDA is unavailable, with a regression check.