Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
200 Open 1,242 Closed
200 Open 1,242 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

OMNIML-5128 Capture Docker experiment id
#1840 opened Jun 27, 2026 by ChenhanYu Collaborator Loading…
17
Fix Nemotron-H PTQ failure on Transformers 5.x with --trust_remote_code (moe_latent_size AttributeError) cherry-pick-0.45.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1839 opened Jun 26, 2026 by Fridah-nv Contributor Loading…
7
specdec(recipe): add MiniMax-M2.7-DFlash streaming multi-node pipeline
#1835 opened Jun 26, 2026 by yeyu-nvidia Contributor Loading…
3 tasks
5
feat(export): quant-aware reverse weight conversion for unified HF export
#1833 opened Jun 26, 2026 by Edwardf0t1 Contributor • Draft
4
Add quant+sparse attention for vLLM serving
#1832 opened Jun 25, 2026 by kaix-nv Contributor • Draft
4
Fix lm_eval_hf freezing issue on multi-gpu slurm interactive node
#1831 opened Jun 25, 2026 by danielkorzekwa Contributor Loading…
4
[Refactor] Extract model specific logics in export lib
#1828 opened Jun 25, 2026 by h-guo18 Contributor • Draft
5
Add Qwen-Image DMD2 PTQ support; save quantizer state (amax) without weights
#1827 opened Jun 25, 2026 by jingyu-ml Contributor Loading…
7
Fix weight-only prequant layernorm export
#1825 opened Jun 25, 2026 by meenchen Contributor • Draft
@meenchen
4
Emit VisualGen-compatible sparse_attention_config for diffusion skip-softmax export
#1816 opened Jun 24, 2026 by jingyu-ml Contributor Loading…
5
Fix AutoQuantize causal LM score scaling
#1810 opened Jun 23, 2026 by realAsma Contributor • Draft
9
Add NVFP4 Conv3d export for diffusers VAE (Wan 2.2)
#1809 opened Jun 23, 2026 by jingyu-ml Contributor Loading…
9
Support FP8 per block (weight + dynamic per token activation) export
#1807 opened Jun 23, 2026 by sugunav14 Contributor Loading…
31
MiniMax-M3 mixed MXFP8-base + NVFP4-experts PTQ export
#1806 opened Jun 23, 2026 by chadvoegele Contributor Loading…
8
Puzzletron tutorial fixes for runtime optimization
#1803 opened Jun 23, 2026 by grzegorz-k-karch Contributor Loading…
@grzegorz-k-karch
9
Add puzzletron eval skill
#1802 opened Jun 23, 2026 by danielkorzekwa Contributor Loading…
@Separius @grzegorz-k-karch
@chochowski @kevalmorabia97 @j-rausch
1
Support INT block scale learning
#1795 opened Jun 22, 2026 by realAsma Contributor • Draft
8
Add VLM pruning and PTQ with image-text calibration (Megatron-Bridge)
#1792 opened Jun 22, 2026 by kevalmorabia97 Collaborator Loading…
50
[OMNIML-5060] cell_t0_d7
#1789 opened Jun 22, 2026 by ChenhanYu Collaborator • Draft
2
[OMNIML-5084] cell_t0_d7
#1788 opened Jun 22, 2026 by ChenhanYu Collaborator • Draft
2
Create adding_new_model_tutorial.md
#1784 opened Jun 22, 2026 by danielkorzekwa Contributor Loading…
6
Add: suppot trt-rtx-abi ep
#1783 opened Jun 22, 2026 by haoxiz-nvidia Contributor Loading…
@haoxiz-nvidia
11
Add: support input_shape_profile for trt-rtx ep
#1782 opened Jun 22, 2026 by haoxiz-nvidia Contributor Loading…
@haoxiz-nvidia
11
Fix low_memory_mode meta-device crash on fused-MoE models
#1781 opened Jun 21, 2026 by abatilo Loading…
5
[Chore]: Update Dflash recipes to use dpace
#1775 opened Jun 20, 2026 by h-guo18 Contributor • Draft
4
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.