Not even running prompts at all

### Custom Node Testing

- [x] 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

I expect to see the progress go from 0% to 100% and get an image

### Actual Behavior

The progress bar stays at 0% for more than 10 minutes. Console shows nothing, my monitoring software shows my GPU usage at less than 9%. CPU also at idle. It's as if ComfyUI is not running my prompts at all.

### Steps to Reproduce

I honestly have no idea how to reproduce other than you wanna install ComfyUI for Linux AND intel GPU (Mine is an ARC A770)

### Debug Logs

```powershell
(venv) mintylagger@mintylagger-ASUS:~/ComfyUI$ python main.py
[INFO] setup plugin alembic.autogenerate.schemas
[INFO] setup plugin alembic.autogenerate.tables
[INFO] setup plugin alembic.autogenerate.types
[INFO] setup plugin alembic.autogenerate.constraints
[INFO] setup plugin alembic.autogenerate.defaults
[INFO] setup plugin alembic.autogenerate.comments
[WARNING] Could not autodetect AIMDO implementation, assuming Nvidia
[INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
[INFO] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
[INFO] Found comfy_kitchen backend cuda: {'available': False, 'disabled': True, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
[INFO] Checkpoint files will always be loaded safely.
[INFO] Total VRAM 15474 MB, total RAM 31971 MB
[INFO] pytorch version: 2.13.0+xpu
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: xpu:0 Intel(R) Arc(TM) A770 Graphics
[INFO] Using pytorch attention
[INFO] Python version: 3.12.3 (main, Jun 19 2026, 12:46:00) [GCC 13.3.0]
[INFO] ComfyUI version: 0.28.0
[INFO] comfy-aimdo version: 0.4.10
[INFO] comfy-kitchen version: 0.2.22
[INFO] comfyui-frontend-package version: 1.47.10
[INFO] comfyui-workflow-templates version: 0.11.17
[INFO] comfyui-embedded-docs version: 0.5.8
[INFO] comfy-kitchen version: 0.2.22
[INFO] comfy-aimdo version: 0.4.10
[INFO] [Prompt Server] web root: /home/mintylagger/ComfyUI/venv/lib/python3.12/site-packages/comfyui_frontend_package/static
[INFO] Asset seeder disabled
[INFO] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
[INFO]
Import times for custom nodes:
[INFO] 0.0 seconds: /home/mintylagger/ComfyUI/custom_nodes/websocket_image_save.py
[INFO]
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
[INFO] Using RAM pressure cache.
[INFO] Starting server

[INFO] To see the GUI go to: http://127.0.0.1:8188
[INFO] got prompt
[INFO] Using pytorch attention in VAE
[INFO] Using pytorch attention in VAE
[INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.bfloat16
[INFO] Requested to load AnimaTEModel_
[INFO] loaded completely; 1136.88 MB loaded, full load: True
[INFO] CLIP/text encoder model load device: xpu:0, offload device: cpu, current: xpu:0, dtype: torch.float16
onednn_verbose,v1,info,oneDNN v3.12.0 (commit 80afa71049cd69a3df32adcccb623b12cd7baa22)
onednn_verbose,v1,info,gpu,runtime:SYCL
onednn_verbose,v1,info,gpu,engine,sycl gpu device count:1
```

### Other

OS: linux mint 22.3 (Ubuntu 24.04)
CPU: AMD RYZEN 7 5700X (Will switch to a 5800X3D as of writing)
RAM: 32GB
GPU: INTEL ARC A770 (16GB VRAM)

Start at the main.py entry point and inspect the execution path after the log line "got prompt" on Linux with an Intel Arc A770 and PyTorch XPU. Use the supplied runtime logs to determine where progress stops after model loading; done means the prompt advances from 0% and produces an image on this setup.

Written by the indexing model from the issue text.