Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
79 Open 462 Closed
79 Open 462 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add support for Qwen3Omni30B thinking model
#856 opened Feb 5, 2026 by ajrasane Loading…
6
[3.1/4] Diffusion Quantized ckpt export - WAN 2.2 14B
#855 opened Feb 5, 2026 by jingyu-ml Loading…
3 of 4 tasks
7
GPTQ official
#853 opened Feb 4, 2026 by sugunav14 • Draft
3
OMNIML-2663] Replace modelopt FP8 QDQ nodes with native ONNX QDQ nodes
#852 opened Feb 4, 2026 by ajrasane Loading…
6
feat: Baseten contrib third-party-dataset support
#851 opened Feb 3, 2026 by michaelfeil Loading…
17
Track global_amax for weight FP4 MSE sweep; Refactor to NVFP4StaticQantizer, NVFP4MSECalibrator
#849 opened Feb 3, 2026 by realAsma Loading…
13
Integrate Automated QDQ placement tool - part 2.3
#846 opened Feb 3, 2026 by willg-nv Loading…
7
Integrate Automated QDQ placement tool - part 2.2
#845 opened Feb 3, 2026 by willg-nv Loading…
8
Integrate Automated QDQ placement tool - part 2.1
#844 opened Feb 3, 2026 by willg-nv Loading…
33
Integrate Automated QDQ placement tool - part 4.3
#843 opened Feb 3, 2026 by willg-nv Loading…
5
Add Automated QDQ placement reference - part 4.2
#842 opened Feb 3, 2026 by willg-nv Loading…
7
Add Automated QDQ placement example - Part 4.1
#841 opened Feb 3, 2026 by willg-nv Loading…
5
GPTQ[1/N]: Implement layer activation getter
#840 opened Feb 2, 2026 by sugunav14 Loading…
1 task done
@sugunav14
15
Integrate Automated QDQ placement tool - part 3.3
#839 opened Feb 2, 2026 by willg-nv Loading…
5
Integrate Automated QDQ autotuner - part 3.2
#838 opened Feb 2, 2026 by willg-nv Loading…
7
Integrate Automated QDQ benchmark - part 3.1
#837 opened Feb 2, 2026 by willg-nv Loading…
7
Add ultrachat 200k to data_utils
#836 opened Feb 1, 2026 by omrib40 Loading…
2
Update the TE support to ModelOPT-PEFT
#835 opened Jan 31, 2026 by jingyu-ml Loading…
@jingyu-ml
5
[3/4] Diffusion Quantized ckpt export
#834 opened Jan 31, 2026 by jingyu-ml Loading…
3 of 4 tasks
@jingyu-ml
10
Fix TEGroupedLinear quantization for expert parallelism (EP > 1)
#833 opened Jan 30, 2026 by yueshen2016 Loading…
@yueshen2016
3
chore(onnx): Remove dead code in find_scales and add test coverage
#832 opened Jan 30, 2026 by shantoislamdev Loading…
2
hardcode support for qwen3vl text only
#826 opened Jan 28, 2026 by h-guo18 • Draft
3
[Minor] fix: do not requantize the scales in FP8 scale sweep calibration
#825 opened Jan 28, 2026 by Fridah-nv Loading…
@Fridah-nv
4
[ONNX][Autocast] Minor bug fixes (AI-assisted)
#822 opened Jan 28, 2026 by galagam Loading…
2
Support Kimi-K2.5 PTQ
#820 opened Jan 27, 2026 by Edwardf0t1 • Draft
8
ProTip! Type g i on any issue or pull request to go back to the issue listing page.