Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
110 Open 563 Closed
110 Open 563 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

Use os.path.join for quant_summary path
#1001 opened Mar 6, 2026 by chadvoegele • Draft
3
ModelOpt Framework, Recipe Lib, converting subset of existing recipes 1/N
#1000 opened Mar 6, 2026 by shengliangxu Loading…
19
updated bmm and matmul for GPT-OSS
#999 opened Mar 6, 2026 by kinjalpatel27 Loading…
2
[ONNX][Autotune] Replace CUDA memory management from CUDART to PyTorch
#998 opened Mar 6, 2026 by gcunhase Loading…
21
Allow basename of dataset paths to match registered names
#997 opened Mar 6, 2026 by AAnoosheh Loading…
11
Draft: merge any_model: mip_and_realize_models
#995 opened Mar 6, 2026 by danielkorzekwa Loading…
1
Draft: merge any model calc one block scores
#994 opened Mar 6, 2026 by danielkorzekwa Loading…
1
Draft: Merging anymodel:build_library_and_stats
#993 opened Mar 6, 2026 by danielkorzekwa Loading…
1
Graph Surgery Framework for TRT-RTX
#992 opened Mar 6, 2026 by hthadicherla Loading…
8
Draft: Merge anymodel pruning
#990 opened Mar 6, 2026 by danielkorzekwa Loading…
2
Draft: anymodel activation scoring
#989 opened Mar 6, 2026 by danielkorzekwa Loading…
3
Jingyux/ltx 2 updates
#988 opened Mar 6, 2026 by jingyu-ml • Draft
@jingyu-ml
3
Skip softmax calibration with list of thresholds
#987 opened Mar 6, 2026 by rohansjoshi Loading…
13
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
fix: https://github.com/NVIDIA/Model-Optimizer/issues/981
#983 opened Mar 5, 2026 by ChenhanYu Loading…
@ChenhanYu
5
Sequential calibrate refactor
#982 opened Mar 5, 2026 by sugunav14 • Draft
2
Support LoRA for MOE Megatron SequentialMLP
#979 opened Mar 5, 2026 by jenchen13 Loading…
8
doc: example demonstrating how to train CosmosReason2 Eagle3
#977 opened Mar 5, 2026 by h-guo18 Loading…
9
[Minor] Improve local hessian and mse calibration
#976 opened Mar 4, 2026 by Fridah-nv Loading…
@Fridah-nv
4
Bump transformers to 5.0
#975 opened Mar 4, 2026 by kevalmorabia97 • Draft
2
Add anymodel-core to feature/puzzletron
#974 opened Mar 4, 2026 by danielkorzekwa Loading…
66
Fix weight-only quantization and export for TEGroupedMLP (MoE models)
#971 opened Mar 4, 2026 by jQizhang Loading…
1 task done
4
Refactor HF _QuantSparseMoe: config-driven token counting, NemotronH detection
#970 opened Mar 4, 2026 by realAsma Loading…
2
[OMNIML-3495] Add TEGroupedMLP export support for NemotronH models
#967 opened Mar 4, 2026 by yueshen2016 Loading…
5
ProTip! Type g i on any issue or pull request to go back to the issue listing page.