Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
162 Open 987 Closed
162 Open 987 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

add vllm dumper
#1507 opened May 16, 2026 by h-guo18 Contributor • Draft
3
Move model-specific PTQ overrides from llm_ptq to YAML recipes
#1506 opened May 16, 2026 by shengliangxu Collaborator • Draft
2
check mean forward KL, EAR, etc for quantized model served with vLLM
#1505 opened May 15, 2026 by Fridah-nv Contributor • Draft
3
Fridah/layerwise mse fix
#1504 opened May 15, 2026 by Fridah-nv Contributor • Draft
2
Add Qwen3.6 W4A16 PTQ recipe
#1503 opened May 15, 2026 by meenchen Contributor Loading…
2
[OMNIML-4750] synth_support
#1502 opened May 15, 2026 by ChenhanYu Collaborator • Draft
2
fix(prune): Minitron HybridModel + Qwen3 fused-TE import + calibration data packing
#1501 opened May 15, 2026 by kevalmorabia97 Collaborator Loading…
89
Add MLA support to vLLM patch
#1499 opened May 15, 2026 by rohansjoshi Contributor Loading…
20
Add active-MoE AutoQuant cost accounting
#1497 opened May 14, 2026 by meenchen Contributor Loading…
7
[OMNIML-4740] synth_support
#1496 opened May 14, 2026 by ChenhanYu Collaborator Loading…
2 of 3 tasks
25
[OMNIML-4730] Support quantized nn.Embedding
#1495 opened May 14, 2026 by ajrasane Contributor Loading…
2
feat: rules-based MTP export for quantized models
#1494 opened May 14, 2026 by yeyu-nvidia Contributor • Draft
3 tasks
4
WIP: Agent Skills Updates From Live Trials
#1493 opened May 14, 2026 by chadvoegele Contributor Loading…
10
Register SyncBatchNorm as quantization module
#1491 opened May 14, 2026 by 5had3z Loading…
2
Add Qwen3VL MCore Export support from PR 895
#1482 opened May 13, 2026 by hychiang-git Contributor Loading…
22
chore: declare contents: read on code_quality workflow
#1480 opened May 13, 2026 by arpitjain099 Loading…
4
[OMNIML-4648] hidden_state_dump_support
#1475 opened May 12, 2026 by ChenhanYu Collaborator • Draft
2
[OMNIML-4652] training_support
#1474 opened May 12, 2026 by ChenhanYu Collaborator • Draft
2
ModelOpt config system documentation
#1472 opened May 12, 2026 by shengliangxu Collaborator • Draft
4
Ssameni/puzzletron bypass 3 integration
#1470 opened May 12, 2026 by Separius Contributor • Draft
3
Ssameni/puzzletron bypass 2 core
#1469 opened May 12, 2026 by Separius Contributor • Draft
3
Split bypass prerequisites
#1468 opened May 12, 2026 by Separius Contributor Loading…
21
[OMNIML-4636] hidden_state_dump_support
#1467 opened May 12, 2026 by ChenhanYu Collaborator • Draft
2
fix: clamp dynamic NVFP4 FP8 scale export
#1465 opened May 12, 2026 by ShawRong Loading…
4
Save next_inputs.pt only for last two layers for layerwise save/restore
#1431 opened May 11, 2026 by sugunav14 Contributor Loading…
11
ProTip! Exclude everything labeled bug with -label:bug.