Skip to content

Issues: pollockjj/ComfyUI-MultiGPU

Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

13 Open 35 Closed
13 Open 35 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Error message occurred while importing the 'ComfyUI-MultiGPU' module.
#58 opened Apr 23, 2025 by revsolutn
UnetLoaderGGUFDisTorchMultiGPU Missing
#56 opened Apr 19, 2025 by DrHojo123
2
UnetLoaderGGUFDisTorchMultiGPU Virtual VRAM issues with HiDream
#55 opened Apr 17, 2025 by Hyunkell
@pollockjj
Support for the the new QuadrupleCLIPLoader for use with new HiDream model enhancement New feature or request released! Enhancement or bug fix released, awaiting feedback
#54 opened Apr 16, 2025 by Opeth66
@pollockjj
6
[Bug] Kijai WanVideoModelLoader missing "offload_device" enhancement New feature or request expected/normal behavior This issue describes normal operation and is not currently targeted for change
#53 opened Apr 14, 2025 by wywywywy
@pollockjj @wywywywy
4
Does this support the latest GGUF torchcompile speed improvements?
#51 opened Apr 12, 2025 by PizzaSlice-cmd
3
Is it worth it using multi-GPU on cards from different generations?
#49 opened Apr 7, 2025 by Djrema
2
the new wanvideomodelloader node cannot work with vram management?
#46 opened Mar 27, 2025 by jasoncow007
Does this actually work when unet is in cpu? question Further information is requested
#44 opened Mar 25, 2025 by Symbiomatrix
@Symbiomatrix @Mescalamba
5
Show device name/model in selection enhancement New feature or request
#40 opened Mar 20, 2025 by without-ordinary
@pollockjj
Question/idea: can layers be preloaded in advance? enhancement New feature or request
#36 opened Mar 13, 2025 by rkfg
@pollockjj
1
Broken if JC2 Node is installed, model alway loading on default CUDA device, no matter what device is chosen in the loader nodes
#34 opened Mar 7, 2025 by ChiliBen
@ChiliBen
2
Multi GPU Memory Cache Issue question Further information is requested
#33 opened Mar 6, 2025 by lanyan520
@lanyan520
4
ProTip! Updated in the last three days: updated:>2025-04-21.