Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
167 Open 1,006 Closed
167 Open 1,006 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

fix: preserve inlined MTP layers for GLM5
#1532 opened May 22, 2026 by Fridah-nv Contributor Loading…
17
[OMNIML-4788] specdec_bench: configuration.json provenance + upload_to_s3
#1531 opened May 21, 2026 by ChenhanYu Collaborator • Draft
22
fix(export): align offloaded modules before pre-quant-scale fuse (#795) bug Something isn't working
#1530 opened May 21, 2026 by realAsma Contributor Loading…
4
[Example]: Add dflash offline example
#1529 opened May 21, 2026 by h-guo18 Contributor • Draft
3
[Tests]: Precommit Check for Spec-Dec Recipes
#1527 opened May 21, 2026 by h-guo18 Contributor Loading…
5
[Recipes]: Add specdec per model recipes
#1526 opened May 21, 2026 by h-guo18 Contributor • Draft
@h-guo18
4
Drive hf_ptq qformat choices from preset YAMLs (remove hardcoded CLI quant configs)
#1525 opened May 21, 2026 by shengliangxu Collaborator Loading…
5
Add YAML based AutoQuantize recipe (currently only CLI is supported)
#1523 opened May 21, 2026 by juhi10071998 Contributor Loading…
4 of 6 tasks
21
Support Mixed precision & Static MSE in MCore; Nemotron Super v3 NVFP4 recipe
#1521 opened May 19, 2026 by jenchen13 Contributor Loading…
11
[fix] Fix NVFP4 AWQ GQA prequant fusion
#1520 opened May 19, 2026 by ShawRong Loading…
5
adding vllm unit tests
#1517 opened May 18, 2026 by kinjalpatel27 Contributor Loading…
41
Megatron-Bridge import example in launcher for Nemotron Super V3
#1516 opened May 18, 2026 by jenchen13 Contributor Loading…
7
fix(quantization): accept QuantizeAlgorithmConfig in get_modelike_from_algo_cfg
#1514 opened May 18, 2026 by javierdejesusda Contributor Loading…
1
7
Support AutoQuant in Megatron-Core
#1512 opened May 18, 2026 by jenchen13 Contributor Loading…
6
[Feat]: Streaming Hidden-states Dataset
#1509 opened May 18, 2026 by h-guo18 Contributor • Draft
2 tasks
@h-guo18
5
[Feat] Vllm Dumper
#1507 opened May 16, 2026 by h-guo18 Contributor • Draft
@h-guo18
4
[OMNIML-3707] Model-specific PTQ recipes bootstrap
#1506 opened May 16, 2026 by shengliangxu Collaborator Loading…
18
check mean forward KL, EAR, etc for quantized model served with vLLM
#1505 opened May 15, 2026 by Fridah-nv Contributor • Draft
4
fix: layerwise mse fix for fuse-experts MoE
#1504 opened May 15, 2026 by Fridah-nv Contributor Loading…
@Fridah-nv
20
[OMNIML-4750] synth_support
#1502 opened May 15, 2026 by ChenhanYu Collaborator • Draft
2
Create shared Megatron calibration forward loop for prune / quantize
#1501 opened May 15, 2026 by kevalmorabia97 Collaborator Loading…
125
Add MLA support to vLLM patch
#1499 opened May 15, 2026 by rohansjoshi Contributor Loading…
23
Add active-MoE AutoQuant cost accounting
#1497 opened May 14, 2026 by meenchen Contributor Loading…
8
[OMNIML-4740] synth_support
#1496 opened May 14, 2026 by ChenhanYu Collaborator Loading…
2 of 3 tasks
41
[OMNIML-4730] Support quantized nn.Embedding
#1495 opened May 14, 2026 by ajrasane Contributor Loading…
9
ProTip! Exclude everything labeled bug with -label:bug.