```CODE: 
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-M2")
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
```

ERROR: 
Traceback (most recent call last):
  File "/tmp/MiniMaxAI_MiniMax-M2_1H18ifN.py", line 20, in <module>
    model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M2")
  File "/tmp/.cache/uv/environments-v2/e4552f1c3ca9047f/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 604, in from_pretrained
    return model_class.from_pretrained(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/e4552f1c3ca9047f/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/e4552f1c3ca9047f/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4881, in from_pretrained
    hf_quantizer, config, dtype, device_map = get_hf_quantizer(
                                              ~~~~~~~~~~~~~~~~^
        config, quantization_config, dtype, from_tf, from_flax, device_map, weights_only, user_agent
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/e4552f1c3ca9047f/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 319, in get_hf_quantizer
    hf_quantizer.validate_environment(
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        dtype=dtype,
        ^^^^^^^^^^^^
    ...<3 lines>...
        weights_only=weights_only,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/e4552f1c3ca9047f/lib/python3.13/site-packages/transformers/quantizers/quantizer_finegrained_fp8.py", line 48, in validate_environment
    raise RuntimeError("No GPU or XPU found. A GPU or XPU is needed for FP8 quantization.")
RuntimeError: No GPU or XPU found. A GPU or XPU is needed for FP8 quantization.