Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
107 Open 603 Closed
107 Open 603 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 calib_include/exclude_modules to calibration algorithms
#1043 opened Mar 16, 2026 by Fridah-nv Loading…
@Fridah-nv
6
[EAGLE] Configurable number of TTT steps
#1042 opened Mar 16, 2026 by benchislett Loading…
5
Simplify puzzletron test configs: use HF model names and shared base YAMLs
#1039 opened Mar 13, 2026 by kevalmorabia97 Loading…
1
Add MoE TEGroupedMLP support for Minitron Pruning
#1038 opened Mar 13, 2026 by kevalmorabia97 • Draft
1 of 3 tasks
3
Fix FP8 ONNX export to use standard QuantizeLinear/DequantizeLinear ops
#1037 opened Mar 13, 2026 by IgorBaratta Loading…
10
Merge mbridge distillation for any_model
#1036 opened Mar 13, 2026 by danielkorzekwa Loading…
6
Merge any_model tutorial
#1035 opened Mar 13, 2026 by danielkorzekwa Loading…
1
[1/n] Add a Triton attention kernel with HF integration
#1034 opened Mar 13, 2026 by kaix-nv Loading…
9
Unify weight_scale_2 between gate_proj/up_proj (and w1/w3) in the HF export path for MOE models
#1033 opened Mar 13, 2026 by Edwardf0t1 Loading…
15
add: ModelOpt Launcher for Slurm job submission
#1031 opened Mar 12, 2026 by ChenhanYu Loading…
45
Add experts_only mode
#1030 opened Mar 12, 2026 by cjluo-nv • Draft
2
Torch PTQ ONNX export example add for windows + small fixes to existing torch onnx export path
#1027 opened Mar 11, 2026 by hthadicherla Loading…
14
Add Full TE Spec support for Megatron Pruning DynamicModules + MoE bug fixes
#1024 opened Mar 11, 2026 by kevalmorabia97 Loading…
4 tasks done
5
Activation hooks redesign (reuse hooks component across both minitron and puzzletron)
#1022 opened Mar 11, 2026 by danielkorzekwa Loading…
27
Dkorzekwa/anymodel gptoss
#1020 opened Mar 11, 2026 by danielkorzekwa Loading…
4
Added 2:4 sparsity to skip softmax method
#1019 opened Mar 11, 2026 by rohansjoshi Loading…
7
[OMNIML-3624] ModelOpt unified entry point, WIP placeholder
#1017 opened Mar 10, 2026 by shengliangxu Loading…
4
add example script for depth importance estimation
#1016 opened Mar 10, 2026 by chochowski Loading…
16
[Feature Request] Support ONNX Q/DQ Autotuning with Subgraph Mode
#1015 opened Mar 10, 2026 by Hale423 Loading…
5 of 6 tasks
22
Add YAML recipe system for model optimization
#1013 opened Mar 10, 2026 by sungsooha Loading…
37
Add agent skills for modelopt
#1011 opened Mar 9, 2026 by kaix-nv • Draft
6
Dkorzekwa/any model other models
#1007 opened Mar 9, 2026 by danielkorzekwa Loading…
43
ModelOpt Framework, Recipe Lib, converting subset of existing recipes 1/N
#1000 opened Mar 6, 2026 by shengliangxu Loading…
59
DMS: Reference kvcompress kernels in the README
#986 opened Mar 5, 2026 by alancucki Loading…
4
Glm5 support
#985 opened Mar 5, 2026 by Aphoh • Draft
2
ProTip! Filter pull requests by the default branch with base:main.