adept/fuyu-8b · Loading the model on multi-gpu setup?

I'm trying to use the following code snippet to load the model on a multi-gpu setup (NVIDIA TESLA T4 x4)

from transformers import FuyuProcessor, FuyuForCausalLM
from PIL import Image

# load model and processor
model_id = "adept/fuyu-8b"
processor = FuyuProcessor.from_pretrained(model_id)
model = FuyuForCausalLM.from_pretrained(model_id, device_map="auto")

# prepare inputs for the model
text_prompt = "Generate a coco-style caption.\n"
image_path = "bus.png"  # https://huggingface.co./adept-hf-collab/fuyu-8b/blob/main/bus.png
image = Image.open(image_path)

inputs = processor(text=text_prompt, images=image, return_tensors="pt")
for k, v in inputs.items():
    inputs[k] = v.to("cuda")

# autoregressively generate text
generation_output = model.generate(**inputs, max_new_tokens=7)
generation_text = processor.batch_decode(generation_output[:, -7:], skip_special_tokens=True)
assert generation_text == ['A bus parked on the side of a road.']

This doesn't seem to work, and the generation process returns an error that "indices should be either on cpu or on the same device as the indexed tensor"

Is there any fix to this, or do I need to use a custom device map?