Qwen_Qwen3-VL-32B-Instruct-FP8_0.txt

```CODE: 
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Qwen/Qwen3-VL-32B-Instruct-FP8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)
```

ERROR: 
Traceback (most recent call last):
  File "/tmp/Qwen_Qwen3-VL-32B-Instruct-FP8_0RYJfB4.py", line 19, in <module>
    pipe = pipeline("image-text-to-text", model="Qwen/Qwen3-VL-32B-Instruct-FP8")
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 1027, in pipeline
    framework, model = infer_framework_load_model(
                       ~~~~~~~~~~~~~~~~~~~~~~~~~~^
        adapter_path if adapter_path is not None else model,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    ...<5 lines>...
        **model_kwargs,
        ^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/pipelines/base.py", line 333, in infer_framework_load_model
    raise ValueError(
        f"Could not load model {model} with any of the following classes: {class_tuple}. See the original errors:\n\n{error}\n"
    )
ValueError: Could not load model Qwen/Qwen3-VL-32B-Instruct-FP8 with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForImageTextToText'>, <class 'transformers.models.qwen3_vl.modeling_qwen3_vl.Qwen3VLForConditionalGeneration'>). See the original errors:

while loading with AutoModelForImageTextToText, an error is thrown:
Traceback (most recent call last):
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/pipelines/base.py", line 293, in infer_framework_load_model
    model = model_class.from_pretrained(model, **kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/pipelines/base.py", line 311, in infer_framework_load_model
    model = model_class.from_pretrained(model, **fp32_kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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.

while loading with Qwen3VLForConditionalGeneration, an error is thrown:
Traceback (most recent call last):
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/pipelines/base.py", line 293, in infer_framework_load_model
    model = model_class.from_pretrained(model, **kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/pipelines/base.py", line 311, in infer_framework_load_model
    model = model_class.from_pretrained(model, **fp32_kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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-v2/49adf985b5e89d74/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.