No backend can handle 'apply_rope': eager: xq: device npu not in {'cuda', 'hpu', 'cpu', 'meta', 'xpu', 'mps'}

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

workflow can be run sucessful

### Actual Behavior

error

### Steps to Reproduce

try flux_example in lastest version v0.9.2
device npu not in {'cuda', 'hpu', 'cpu', 'meta', 'xpu', 'mps'}

### Debug Logs

```powershell
Checkpoint files will always be loaded safely.
Total VRAM 62420 MB, total RAM 2062680 MB
pytorch version: 2.7.1+cpu
Set vram state to: HIGH_VRAM
Device: npu
Found comfy_kitchen backend cuda: {'available': False, 'disabled': True, 'unavailable_reason': 'Extension file not found: /usr/local/python3.11.13/lib/python3.11/site-packages/comfy_kitchen/backends/cuda/_C.abi3.so', 'capabilities': []}
Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': "ImportError: No module named 'triton'", 'capabilities': []}
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Using pytorch attention
Python version: 3.11.13 (main, Nov 2 2025, 08:46:33) [GCC 11.4.0]
ComfyUI version: 0.9.2
****** User settings have been changed to be stored on the server instead of browser storage. ******
****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ******
ComfyUI frontend version: 1.36.14
[Prompt Server] web root: /usr/local/python3.11.13/lib/python3.11/site-packages/comfyui_frontend_package/static

Import times for custom nodes:
0.0 seconds: /ComfyUI/custom_nodes/websocket_image_save.py

Context impl SQLiteImpl.
Will assume non-transactional DDL.
Context impl SQLiteImpl.
Will assume non-transactional DDL.
Running upgrade -> 0001_assets, Initial assets schema
Revision ID: 0001_assets
Revises: None
Create Date: 2025-12-10 00:00:00
Database upgraded from None to 0001_assets
Assets scan(roots=['models']) completed in 0.057s (created=11, skipped_existing=0, total_seen=11)
Starting server

To see the GUI go to: http://194.0.65.4:8288
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: npu:0, offload device: npu:0, dtype: torch.bfloat16
model weight dtype torch.bfloat16, manual cast: None
model_type FLUX
clip missing: ['text_projection.weight']
Requested to load FluxClipModel_
loaded completely; 9319.23 MB loaded, full load: True
CLIP/text encoder model load device: npu:0, offload device: npu:0, current: npu:0, dtype: torch.float16
Requested to load Flux
loaded completely; 22700.13 MB loaded, full load: True
0%| | 0/20 [00:00