RuntimeError after using apply_group_offloading on diffusers: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

Can anyone help me?
I used WanX's diffusers and used apply_group_offloading according to url: https://huggingface.co/docs/diffusers/main/en/optimization/memory.
The code is as follows:
```
image_encoder = CLIPVisionModel.from_pretrained(local_model_path, subfolder="image_encoder", torch_dtype=torch.float32)
vae = AutoencoderKLWan.from_pretrained(local_model_path, subfolder="vae", torch_dtype=torch.float32)
scheduler_b = UniPCMultistepScheduler(prediction_type="flow_prediction", use_flow_sigmas=True, flow_shift=5.0)
pipe = WanImageToVideoPipeline.from_pretrained(local_model_path, vae=vae, image_encoder=image_encoder, scheduler=scheduler_b, torch_dtype=torch.bfloat16)
pipe.transformer.enable_group_offload(onload_device=torch.device("cuda"), offload_device=torch.device("cpu"), offload_type="block_level", num_blocks_per_group=1, use_stream=True)
apply_group_offloading(pipe.text_encoder, onload_device=torch.device("cuda"), offload_type="block_level", num_blocks_per_group=1, use_stream=True)
apply_group_offloading(pipe.vae, onload_device=torch.device("cuda"), offload_type="block_level", num_blocks_per_group=1, use_stream=True)
apply_group_offloading(pipe.image_encoder, onload_device=torch.device("cuda"), offload_type="block_level", num_blocks_per_group=1, use_stream=True)
```

Then print the device information:
`Before apply_offload:
text_encoder device: cpu
transformer device: cpu
vae device: cpu
image_encoder device: cpu
start to group_offload_block_1_stream
After apply_offload:
text_encoder device: cpu
transformer device: cpu
vae device: cpu
image_encoder device: cpu`

Finally, an exception is thrown:
` return F.conv3d(
^^^^^^^^^
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same`

Does anyone know how to fix this? Thanks a lot.

Start by reproducing the WanImageToVideoPipeline setup with apply_group_offloading and inspect the device and dtype of the pipeline components before the failing F.conv3d call. Compare the offloading configuration with the reported CPU weights and CUDA input; done means the pipeline runs without the reported input/weight type mismatch.

Vom Indexierungsmodell aus dem Issue-Text verfasst.