Skip to content

Issues: mit-han-lab/nunchaku

User Slack and Wechat Groups for Discussion
#149 opened Mar 6, 2025 by lmxyy
Open
Preliminary Windows Wheels Released!
#169 opened Mar 9, 2025 by lmxyy
Open
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

49 Open 104 Closed
49 Open 104 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

Preliminary Windows Wheels Released!
#169 opened Mar 9, 2025 by lmxyy
Without modifying the RANK hierarchy, it will fail to compile on my computer
#168 opened Mar 8, 2025 by flybirdxx
Please support Chroma is a 8.9 billion parameter rectified flow transformer capable of generating images from text descriptions. Based on FLUX.1 [schnell] with heavy architectural modifications.
#167 opened Mar 8, 2025 by nitinmukesh
Build Error for 0.1.4 in windows10
#166 opened Mar 8, 2025 by lestersssss
1
Build Failure on Windows 11: nvcc “compiler is out of heap space” error in nunchaku v0.1.4
#165 opened Mar 8, 2025 by akashzeno
Please support Wan 2.1 1.3B / 14B text and image to video models
#163 opened Mar 8, 2025 by nitinmukesh
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
#162 opened Mar 8, 2025 by chensyo
7
Import Failed on Arch Linux ComfyUI SVDQuant
#161 opened Mar 8, 2025 by zono50
cannot import name 'comfyui2diffusers' from 'nunchaku.lora.flux
#160 opened Mar 8, 2025 by jokerconnor
3
Support for RTX 2060 Super 8GB VRAM?
#159 opened Mar 8, 2025 by krigeta
5
new version (IMPORT FAILED): F:\ComfyUI\ComfyUI\custom_nodes\svdquant bug Something isn't working in progress
#158 opened Mar 8, 2025 by xueqing0622
@lmxyy
13
CUDA error: no kernel image is available for execution on the device (at E:\home\nunchaku\src\kernels\awq\gemv_awq.cu:313)
#153 opened Mar 7, 2025 by Jasonzhangf
Conflicts with the latest version of Triton, ComfyUI cannot load the nunchaku node.
#152 opened Mar 7, 2025 by edisonchan
how to convert other flux checkpoint?
#151 opened Mar 7, 2025 by xueqing0622
ComfyUI how to remove the warning "3d torch.Tensor is deprecated.Please remove the batch dimension and pass it as a 2d torch Tensor"
#150 opened Mar 6, 2025 by LiJT
1
User Slack and Wechat Groups for Discussion
#149 opened Mar 6, 2025 by lmxyy
AssertionError: assert image_rotary_emb.shape[2] == batch_size * (txt_tokens + img_tokens) bug Something isn't working in progress
#148 opened Mar 6, 2025 by O-O1024
@lmxyy
2
NunchakuFluxTransformer2dModel.from_pretrained lags/stuck for ~20 minutes after download is complete on CUDA v12.7 and/or NVIDIA driver v565 bug Something isn't working in progress
#147 opened Mar 5, 2025 by josephrocca
@lmxyy
How to use nunchaku for inference instead of torch？ enhancement New feature or request question Further information is requested
#143 opened Mar 4, 2025 by zfnice
Naive version without kernel fusion
#142 opened Mar 4, 2025 by joe-zxh
1
comfyui crack with error :Unable to pin memory: operation not supported
#141 opened Mar 4, 2025 by czcz1024
5
Load multiple LoRAs enhancement New feature or request
#140 opened Mar 4, 2025 by bot66
linux python=3.10.15, torch2.6 Installation failure
#136 opened Mar 3, 2025 by nongyu-gpu
1
Computer get stucked after several correct runs bug Something isn't working help wanted Extra attention is needed urgent
#133 opened Mar 2, 2025 by joe-zxh
@lmxyy
9
Why has the LoRA become so big?After conversion, the size is two times larger. enhancement New feature or request
#132 opened Mar 2, 2025 by Erwin11
@lmxyy
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.