ComfyUI Job stuck at 0% #2663
Description
Hello guys! I'm facing a problem and I would like to get some help. I'm using ComfyUI-Manager for the first time, and tried to do the configuration, however, when I run any job, the job get stuck at 0% at progress bar, no matter what type of job do we have. For example, I have this log since the startup, and this job was stuck for more than 6 hours straight without any progress. Do you know what can I do to make a setup working properly? Thanks in advance!
📦[igor@ubuntu-comfyui app]$ HSA_OVERRIDE_GFX_VERSION=10.3.0 python3 main.py --lowvram --listen --use-split-cross-attention --fp16-unet
[START] Security scan
[ComfyUI-Manager] Using `uv` as Python module for pip operations.
Using Python 3.10.12 environment at: /usr
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-03-02 13:08:26.839
** Platform: Linux
** Python version: 3.10.12 (main, Jan 26 2026, 14:55:28) [GCC 11.4.0]
** Python executable: /usr/bin/python3
** ComfyUI Path: /run/media/igor/Disco III/pinokio/api/comfy.git/app
** ComfyUI Base Folder Path: /run/media/igor/Disco III/pinokio/api/comfy.git/app
** User directory: /run/media/igor/Disco III/pinokio/api/comfy.git/app/user
** ComfyUI-Manager config path: /run/media/igor/Disco III/pinokio/api/comfy.git/app/user/__manager/config.ini
** Log path: /run/media/igor/Disco III/pinokio/api/comfy.git/app/user/comfyui.log
Using Python 3.10.12 environment at: /usr
Using Python 3.10.12 environment at: /usr
[ComfyUI-Manager] PyTorch is not installed
Using Python 3.10.12 environment at: /usr
Resolved 1 package in 300ms
error: Failed to install: comfyui_frontend_package-1.36.14-py3-none-any.whl (comfyui-frontend-package==1.36.14)
Caused by: failed to create directory `/usr/local/lib/python3.10/dist-packages/comfyui_frontend_package`: Permission denied (os error 13)
[ComfyUI-Manager] Failed to restore comfyui-frontend-package
Command '['/usr/bin/python3', '-m', 'uv', 'pip', 'install', 'comfyui-frontend-package==1.36.14']' returned non-zero exit status 2.
Prestartup times for custom nodes:
0.8 seconds: /run/media/igor/Disco III/pinokio/api/comfy.git/app/custom_nodes/ComfyUI-Manager
Checkpoint files will always be loaded safely.
Total VRAM 8176 MB, total RAM 15876 MB
pytorch version: 2.5.0.dev20240802+rocm6.0
AMD arch: gfx1030
ROCm version: (6, 0)
Warning, could not set allow_fp16_bf16_reduction_math_sdp
Set vram state to: LOW_VRAM
Device: cuda:0 AMD Radeon RX 6600 : native
Using async weight offloading with 2 streams
Enabled pinned memory 15082.0
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
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']}
Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Using split optimization for attention
Python version: 3.10.12 (main, Jan 26 2026, 14:55:28) [GCC 11.4.0]
ComfyUI version: 0.9.2
ComfyUI frontend version: 1.36.14
[Prompt Server] web root: /home/igor/.local/lib/python3.10/site-packages/comfyui_frontend_package/static
### Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
### ComfyUI Version: v0.9.2-5-g9125613b | Released on '2026-01-15'
Import times for custom nodes:
0.0 seconds: /run/media/igor/Disco III/pinokio/api/comfy.git/app/custom_nodes/websocket_image_save.py
0.2 seconds: /run/media/igor/Disco III/pinokio/api/comfy.git/app/custom_nodes/ComfyUI-Manager
Context impl SQLiteImpl.
Will assume non-transactional DDL.
Assets scan(roots=['models']) completed in 0.031s (created=0, skipped_existing=13, total_seen=13)
Starting server
To see the GUI go to: http://0.0.0.0:8188
To see the GUI go to: http://[::]:8188
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
Requested to load SD1ClipModel
loaded completely; 235.84 MB loaded, full load: True
CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load BaseModel