Skip to content

Issues: intel/auto-round

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

12 Open 55 Closed
12 Open 55 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

Cannot quantize Qwen2-VL-72B-Instruct on a single gpu card
#389 opened Dec 17, 2024 by WeiweiZhang1
@n1ck-guo
2
export.py L76: Saving quantized model to auto_awq format crash with AssertionError
#388 opened Dec 16, 2024 by fbaldassarri
1
tune nvidia/Hymba-1.5B-Instruct exception
#374 opened Dec 6, 2024 by wenhuach21
calibration dataset enhancement
#366 opened Dec 3, 2024 by wenhuach21
autoround tuning is not stable for llama3.1/3.3 70B and variants
#355 opened Nov 29, 2024 by wenhuach21
1
[low priority]vlm export to autoawq
#353 opened Nov 28, 2024 by wenhuach21
@n1ck-guo
consecutive quantization for the same model with different config bug
#352 opened Nov 27, 2024 by wenhuach21
@wenhuach21
[New feature request] support exporting to guff at group_size 32
#288 opened Oct 23, 2024 by wenhuach21
[New Feature Request] layer wise sensitivity analysis
#253 opened Sep 11, 2024 by wenhuach21
@n1ck-guo
[Low priority]add support of quarot，spinquant and DuQuant
#219 opened Aug 12, 2024 by wenhuach21
@wenhuach21 @WeiweiZhang1
1
support low_cpu_mem at packing stage and for safetensor
#194 opened Jul 19, 2024 by wenhuach21
@n1ck-guo
AutoRound currently does not support numpy2x.
#157 opened Jun 17, 2024 by Kaihui-intel
@yintong-lu
ProTip! no:milestone will show everything without a milestone.