Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
214 Open 1,271 Closed
214 Open 1,271 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

ci: give non-PR code quality runs distinct concurrency groups
#1894 opened Jul 2, 2026 by arham766 Loading…
2
ci: run path-gated unit test lanes on push events
#1893 opened Jul 2, 2026 by arham766 Loading…
2
ci: scope bump_uv_lock change detection to uv.lock
#1892 opened Jul 2, 2026 by arham766 Loading…
2
ci: gate example and GPU tests on changes to their own runner and cache action
#1891 opened Jul 2, 2026 by arham766 Loading…
2
Create a tool for data blend preparation to enable fast experimentation with distillation
#1888 opened Jul 2, 2026 by danielkorzekwa Contributor Loading…
10
feat(speculative): add Qwen3-VL support for DFlash training
#1887 opened Jul 2, 2026 by skierat Contributor Loading…
5
specdec_bench modelopt release
#1886 opened Jul 2, 2026 by talorabr Loading…
5
fix: handle Qwen3-VL-MoE expert dimensions
#1885 opened Jul 2, 2026 by harshtripathi6 Loading…
1
6
Add LAQ/LSQ support and recipes
#1884 opened Jul 2, 2026 by realAsma Contributor • Draft
3
Add TensorQuantizer Random Hadamard rotation seed
#1883 opened Jul 2, 2026 by realAsma Contributor • Draft
2
draft: Add Decoupled Scale Search for NVFP4 local_hessian calibration
#1881 opened Jul 1, 2026 by Fridah-nv Contributor • Draft
2
Add TensorQuantizer rotate-back mode
#1879 opened Jul 1, 2026 by realAsma Contributor • Draft
11
Add normalized and group-boundary AutoQuant scoring
#1878 opened Jul 1, 2026 by meenchen Contributor • Draft
4
Add deployment test cases, fix deployment-related issues, and remove private models
#1873 opened Jul 1, 2026 by nvSiruiW Contributor Loading…
14
Create a user guide: ModelOpt for Researchers: Fast Experimentation Workflows
#1872 opened Jul 1, 2026 by danielkorzekwa Contributor Loading…
6
Add recipe used for Qwen3.5 397B NVFP4 V2 checkpoint
#1868 opened Jun 30, 2026 by sugunav14 Contributor Loading…
8
fix: prevent UnboundLocalError masking real errors in fsdp2_aware_weight_update
#1860 opened Jun 30, 2026 by dinhxuanvu Loading…
1
2
Add AutoQuantize recipe support
#1856 opened Jun 29, 2026 by juhi10071998 Contributor Loading…
@juhi10071998
57
Reintroduce AIPerf for performance benchmarking, clean up docs and text
#1855 opened Jun 29, 2026 by nfasfous Loading…
2
[Feat]: Support Dspark
#1849 opened Jun 29, 2026 by h-guo18 Contributor Loading…
@h-guo18
10
Add LAQ NVFP4 export support
#1847 opened Jun 28, 2026 by realAsma Contributor • Draft
2
[Feat]: Add Final Norm for vLLM Hidden Extractor
#1846 opened Jun 28, 2026 by h-guo18 Contributor Loading…
@h-guo18
23
docs(eval): add NEL v0.3.0 migration guide + example configs
#1845 opened Jun 28, 2026 by hychiang-git Contributor Loading…
26
refactor(examples): consolidate puzzletron examples under examples/pruning/puzzletron
#1841 opened Jun 27, 2026 by valter-silva-au Loading…
1
6
specdec(recipe): add MiniMax-M2.7-DFlash streaming multi-node pipeline
#1835 opened Jun 26, 2026 by yeyu-nvidia Contributor Loading…
3 tasks
7
ProTip! no:milestone will show everything without a milestone.