Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
196 Open 1,167 Closed
196 Open 1,167 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

[NVBug 6287315] Fix unified HF export for Llama4 MoE models cherry-pick-0.45.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1744 opened Jun 16, 2026 by shengliangxu Collaborator Loading…
3
fix(autocast): add missing guard for use_standalone_type_inference
#1743 opened Jun 15, 2026 by agkphysics Loading…
2
Remove unsafe torch.load from examples/diffusers/fastgen cherry-pick-0.45.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1740 opened Jun 15, 2026 by kevalmorabia97 Collaborator Loading…
3
Re-organize Changelog for 0.45 cherry-pick-0.45.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1737 opened Jun 15, 2026 by kevalmorabia97 Collaborator Loading…
2
[OMNIML-5024] cell_t0_d3
#1733 opened Jun 15, 2026 by ChenhanYu Collaborator • Draft
2
fix(megatron): handle MambaMixer conv1d refactor in importer/exporter
#1730 opened Jun 15, 2026 by AAnoosheh Contributor Loading…
2 tasks done
@AAnoosheh
3
[DRAFT] Add heterogeneous AnyModel distillation example for Puzzletron.
#1725 opened Jun 15, 2026 by chochowski Contributor Loading…
1
11
[Feat]:Support DPace
#1724 opened Jun 15, 2026 by h-guo18 Contributor Loading…
@ChenhanYu
10
Fix autotune warm restart to retry failed schemes
#1722 opened Jun 15, 2026 by willg-nv Contributor Loading…
2
[OMNIML-5091] specdec_bench cell t0_d7 — nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 / MTP / trtllm
#1721 opened Jun 14, 2026 by ChenhanYu Collaborator • Draft
3
[Quantization] Support NVFP4 for inline-swiglu fused MoE experts (MiniMax-M3 / MiniMaxM3VLExperts)
#1719 opened Jun 14, 2026 by yifjiang • Draft
4 of 5 tasks
2
[OMNIML-5072] Triton fakequant adapter for N-quantizer per-expert path
#1717 opened Jun 14, 2026 by hychiang-git Contributor • Draft
2
Support Mamba direct conv1d quant export
#1716 opened Jun 14, 2026 by mxinO Contributor • Draft
5
[OMNIML-5100] specdec_bench cell t1_d7 — nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 / MTP / vllm
#1715 opened Jun 14, 2026 by ChenhanYu Collaborator • Draft
3
[OMNIML-5098] cell_t0_d7
#1714 opened Jun 14, 2026 by ChenhanYu Collaborator • Draft
2
[OMNIML-5097] cell_t0_d3
#1713 opened Jun 14, 2026 by ChenhanYu Collaborator • Draft
2
fix(quantization): detect fused MoE experts without act_fn (MiniMax-M3)
#1711 opened Jun 14, 2026 by Edwardf0t1 Contributor Loading…
3
[Feat]: Domino support
#1710 opened Jun 13, 2026 by h-guo18 Contributor Loading…
@h-guo18
20
Harden remote artifact path reads
#1709 opened Jun 13, 2026 by fallintoplace Loading…
2
Add support for dLLM encoder-decoder models (DiffusionGemma) [tied-weight PTQ export support ]
#1707 opened Jun 13, 2026 by juhi10071998 Contributor Loading…
17
Qwen-Image diffusers PTQ: FP8 / NVFP4 / NVFP4-SVDQuant HF checkpoints
#1706 opened Jun 12, 2026 by jingyu-ml Contributor Loading…
11
refactor(examples): consolidate vlm_ptq into llm_ptq
#1705 opened Jun 12, 2026 by Edwardf0t1 Contributor Loading…
14
Detect fused experts using _apply_gate as activation marker
#1703 opened Jun 12, 2026 by Mapika Loading…
2
Update roadmap link in README.md
#1700 opened Jun 12, 2026 by Trenton-Starkey Loading…
2
[OMNIML-4760] synth_support
#1696 opened Jun 12, 2026 by ChenhanYu Collaborator • Draft
2
ProTip! Adding no:label will show everything without a label.