Skip to content

Issues: mit-han-lab/nunchaku

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

17 Open 19 Closed
17 Open 19 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

Precision used in multi head attention layer
#37 opened Nov 26, 2024 by kimdaeun00
When set DEBUG = True in setup.py, I get the following error:
#36 opened Nov 25, 2024 by Lenan22
4
New Flux Fill Support
#34 opened Nov 22, 2024 by chuck-ma
2
Implementation dtails: GEMM_W4A4::quantize behavior different from the paper
#33 opened Nov 22, 2024 by xmfbit
Quality comparison: SVDQuant vs GGUF Q4 ?
#31 opened Nov 21, 2024 by marvin-0042
1
Is that possible to support any torch model?
#30 opened Nov 21, 2024 by microbenh
1
A100 RuntimeError: CUDA error: no kernel image is available for execution on the device
#27 opened Nov 18, 2024 by marvin-0042
4
什么时候支持comfyui
#26 opened Nov 18, 2024 by StartHua
Python-level Linear Modularization.
#24 opened Nov 14, 2024 by Artiprocher
1
Can nunchaku support more Video-generator model？
#23 opened Nov 14, 2024 by philipwan
6
Running 'example. py' in a Docker container can cause the system to freeze or be forced to shut down
#22 opened Nov 13, 2024 by ziyaxuanyi
4
Question about why getting blank image when using flux ControlNet.
#20 opened Nov 13, 2024 by chuck-ma
7
Please create a comfy node to use it
#14 opened Nov 11, 2024 by wardensc2
2
How to quantize a custom Flux model? For example, lightweight models like Flux Lite that have removed some double blocks.
#13 opened Nov 11, 2024 by kelisiya
2
RuntimeError: Error compiling objects for extension
#12 opened Nov 11, 2024 by 973398769
7
is support controlnet and ip-adapter?
#3 opened Nov 9, 2024 by libai-lab
4
Any chance for MPS?
#2 opened Nov 8, 2024 by cchance27
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.