Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
44 Open 332 Closed
44 Open 332 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

[5336829][AutoCast] Support subgraphs
#659 opened Dec 7, 2025 by galagam Loading…
config file based modelopt config 1/N
#657 opened Dec 6, 2025 by shengliangxu • Draft
2
[OMNIML-2244] Add E2E example for mixed precision quantization and ONNX export
#656 opened Dec 5, 2025 by ajrasane Loading…
1
Kimi-k2 calib+export
#655 opened Dec 5, 2025 by jingyu-ml Loading…
11
Support model export for int4 wo
#653 opened Dec 5, 2025 by meenchen Loading…
@meenchen
1
[5676209][ONNX][Autocast] Add check for input bs vs calibration data bs
#652 opened Dec 5, 2025 by gcunhase Loading…
1
[Bug Fix]: NVBug 5711927
#651 opened Dec 5, 2025 by sugunav14 Loading…
@sugunav14
2
Noeyy/add new ckpts test cases
#650 opened Dec 5, 2025 by noeyy-mino Loading…
1
[NVBUG: 5701937]Clear GPU cache for 3D weight tensors
#649 opened Dec 4, 2025 by cjluo-nv Loading…
1
Bump the pip group across 4 directories with 2 updates dependencies Pull requests that update a dependency file python Pull requests that update python code
#646 opened Dec 4, 2025 by dependabot bot Loading…
1
Added support for TElinear ops
#632 opened Dec 2, 2025 by kinjalpatel27 Loading…
7
Address security concerns in code
#626 opened Dec 2, 2025 by kevalmorabia97 Loading…
2 of 3 tasks
5
refactor: eagle config rewrite; update doc
#624 opened Dec 2, 2025 by h-guo18 Loading…
@h-guo18
2
Updated dependencies in Windows examples
#622 opened Dec 1, 2025 by hthadicherla Loading…
4
Optimize calibrate_draft_vocab to read only required lines when calib…
#618 opened Nov 27, 2025 by Ofir408 Loading…
3
MLA eagle for K2
#615 opened Nov 27, 2025 by h-guo18 • Draft
1
draft: Add per block MSE for NVFP4 and INT4
#613 opened Nov 27, 2025 by Fridah-nv • Draft
@Fridah-nv
4
Convert compressed-tensor int4 format to GPTQ int4 format
#590 opened Nov 20, 2025 by Edwardf0t1 Loading…
2
Yeyu/remove embedding from eagle
#585 opened Nov 20, 2025 by yeyu-nvidia • Draft
1
support for newer checkpoints
#582 opened Nov 20, 2025 by binghanc • Draft
1
Feat: SGL backend for online SD training
#564 opened Nov 14, 2025 by h-guo18 Loading…
@h-guo18
7
GPTQ Lite implementation
#555 opened Nov 13, 2025 by sugunav14 Loading…
1 of 2 tasks
@sugunav14
13
[OMNIML-2850] [3/n] Adds sparse attention calibration
#538 opened Nov 11, 2025 by kaix-nv Loading…
2
[OMNIML-2852] [2/n] Add Core Sparse Attention Infrastructure
#527 opened Nov 7, 2025 by kaix-nv Loading…
13
parallel eagle draft
#523 opened Nov 6, 2025 by yeyu-nvidia • Draft
2
ProTip! Adding no:label will show everything without a label.