Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
138 Open 853 Closed
138 Open 853 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-4021]: align local JSONL loading with HF datasets path + keep original behaviour
#1345 opened Apr 24, 2026 by shengliangxu Collaborator Loading…
3 tasks done
4
[minor] fixes for layerwise calib + MSE
#1344 opened Apr 24, 2026 by Fridah-nv Contributor Loading…
@Fridah-nv
4
Support EP mcore import for TE Spec and Fix mamba moe config
#1342 opened Apr 24, 2026 by jenchen13 Contributor Loading…
5
DSV4 dequant on the fly
#1341 opened Apr 24, 2026 by mxinO Contributor • Draft
4
[NVBug 6108145] Fix PTQ calibration and export for fused-experts MoE (Qwen3.5-MoE VLM) bug Something isn't working cherry-pick-0.44.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1340 opened Apr 24, 2026 by meenchen Contributor Loading…
@meenchen
19
Update
#1338 opened Apr 23, 2026 by jingyu-ml Contributor • Draft
@jingyu-ml
3
[OMNIML-3934] Guidelines and precommit hook for pydantic backward compatbility
#1333 opened Apr 23, 2026 by jenchen13 Contributor Loading…
8
fix incomplete mapping of safetensors in generated puzzletron checkpoint
#1330 opened Apr 23, 2026 by grzegorz-k-karch Contributor Loading…
16
[Refactor] speculative decoding: use mto config subsystem
#1328 opened Apr 23, 2026 by h-guo18 Contributor Loading…
@h-guo18
11
Quantize lm_head + embedding for Nemotron-H, add NVFP4 W4A16 recipe
#1327 opened Apr 22, 2026 by ajrasane Contributor Loading…
3 of 5 tasks
@ajrasane
12
Update the DMD2 at the first stage
#1326 opened Apr 22, 2026 by jingyu-ml Contributor • Draft
@jingyu-ml
13
Add Nemotron-Nano-9B-v2 → Pruned 7B tutorial: end-to-end Prune + Distill + Eval + Quantize + vLLM deployment cherry-pick-0.44.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1325 opened Apr 22, 2026 by kevalmorabia97 Collaborator Loading…
15
[NVBug 6102977] Add _disable_use_cache context manager to fix PTQ AttributeError on custom configs bug Something isn't working cherry-pick-0.44.0 After code freeze, cherry-pick to release branch for next rc (bulk update). Only for bug fixes / doc
#1324 opened Apr 22, 2026 by meenchen Contributor Loading…
@meenchen
3
Fix NVFP4 quantization for Qwen3.x MoE models (4 silent-failure bugs)
#1323 opened Apr 22, 2026 by erictinkeredapps Loading…
4
Add demo (Puzzletron and Minitron guide) in Model-Optimizer/examples/pruning/ with README and notebooks documentation Improvements or additions to documentation
#1320 opened Apr 22, 2026 by achidiac-nv Loading…
@achidiac-nv
37
VSA support for Wan 2.2 and LTX2
#1315 opened Apr 22, 2026 by jingyu-ml Contributor Loading…
@jingyu-ml
19
Support NVFP4 W4A16 quantization
#1313 opened Apr 22, 2026 by hychiang-git Contributor Loading…
8
fix: layerwise calibration backward-compat, recipe split, batch-size guard
#1310 opened Apr 21, 2026 by realAsma Contributor Loading…
2 tasks done
35
fix: preserve q/k/v quantizer mapping in AST attention patching
#1307 opened Apr 21, 2026 by Brumbelow Loading…
4 tasks done
1
5
fix: disable nvidia-resiliency-ext when incompatible with container PyTorch
#1304 opened Apr 21, 2026 by ChenhanYu Collaborator • Draft
1 task done
4
[3/3][Refactor]: Extract HFSpecDecMixin for HF spec-decoding plugins
#1297 opened Apr 19, 2026 by h-guo18 Contributor • Draft
2
keep deploy cases and Eagle fixes for merge
#1287 opened Apr 17, 2026 by nvSiruiW Loading…
5
Update excluded modules for Qwen3.5 dense PTQ
#1284 opened Apr 17, 2026 by amukkara Loading…
2
Add qwen3 moe experts only test
#1274 opened Apr 16, 2026 by cjluo-nv Collaborator Loading…
12
SpecDec Bench: April Update
#1272 opened Apr 16, 2026 by IzzyPutterman Contributor Loading…
37
ProTip! Exclude everything labeled bug with -label:bug.