Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
126 Open 701 Closed
126 Open 701 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

Refactor Qwen3.5 MoE quantization to use _QuantFunctionalMixin
#1170 opened Apr 2, 2026 by cjluo-nv Loading…
4 tasks
3
Bump the uv group across 6 directories with 6 updates dependencies Pull requests that update a dependency file python:uv Pull requests that update python:uv code
#1168 opened Apr 2, 2026 by dependabot bot Loading…
1
Add the Skip softmax for diffusion
#1166 opened Apr 2, 2026 by jingyu-ml • Draft
@jingyu-ml
4
recipes doc
#1165 opened Apr 2, 2026 by shengliangxu • Draft
4
Add export support for Qwen3VL MoE experts with ModuleList linear layers
#1164 opened Apr 1, 2026 by shengliangxu • Draft
4
Added support for MoE for vllm >= 0.14.0rc1
#1162 opened Apr 1, 2026 by kinjalpatel27 • Draft
7
Fix MoE quantization tests and add sync_expert_weight_amax option
#1158 opened Apr 1, 2026 by jenchen13 Loading…
5
Fix[bug] ONNX models generated by llm_export.py are missing some i/o
#1157 opened Apr 1, 2026 by Ratheesh1104 Loading…
5
[fix] AutoQuant: clamp instead of use fp64 in auto quant score
#1156 opened Apr 1, 2026 by Fridah-nv Loading…
3
fix spelling errors
#1153 opened Apr 1, 2026 by noeyy-mino Loading…
4
Intermediate checkpointing for sequential calibration
#1152 opened Mar 31, 2026 by sugunav14 Loading…
14
Add Claude Code plugin marketplace for ModelOpt agent skills
#1141 opened Mar 30, 2026 by kaix-nv Loading…
8
Fix parquet loading crash from datasets version mismatch
#1140 opened Mar 30, 2026 by yeyu-nvidia Loading…
2 tasks
5
[chore]: weekly bump of uv.lock on main (2026-03-30)
#1139 opened Mar 30, 2026 by github-actions bot Loading…
3
[Speculative Decoding] Refactor EAGLE3 training to YAML-based config and recipe system
#1134 opened Mar 29, 2026 by h-guo18 Loading…
@h-guo18
31
Add Agent Deployment skill for model serving
#1133 opened Mar 28, 2026 by kaix-nv Loading…
38
Add Agent Evaluation skill for accuracy benchmarking
#1132 opened Mar 28, 2026 by kaix-nv Loading…
30
Add clear instructions for generating quantized ONNX models (fixes #799)
#1129 opened Mar 28, 2026 by Pritiks23 Loading…
1
4
add: DFlash block diffusion speculative decoding
#1128 opened Mar 27, 2026 by ChenhanYu Loading…
13
[4/n] Add vLLM integration for modelopt sparse attention
#1127 opened Mar 27, 2026 by kaix-nv Loading…
14
Add DeepSeek MoE detection and export mapping in HF PTQ/export path
#1125 opened Mar 26, 2026 by Charles-JCJ Loading…
5
Refine _extract_layer_prefixes to better handle mtp modules
#1124 opened Mar 26, 2026 by Edwardf0t1 Loading…
6
Merge puzzletron compression algorithm
#1121 opened Mar 25, 2026 by danielkorzekwa Loading…
45
Add custom MoE quantization guide for HuggingFace models
#1118 opened Mar 25, 2026 by cjluo-nv Loading…
5
Add nvfp4_mse and nvfp4_local_hessian options to the ptq script. cherry-pick After code freeze, cherry-pick into release branch for next rc. Only for bug fixes and doc updates
#1113 opened Mar 24, 2026 by bkartal-dev Loading…
9
ProTip! no:milestone will show everything without a milestone.