Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
64 Open 396 Closed
64 Open 396 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 FP8 sweep and step_size flag
#758 opened Jan 9, 2026 by Fridah-nv • Draft
4
[5763448] Fix Resize input type mismatch error
#757 opened Jan 9, 2026 by gcunhase Loading…
1
Support VLM calibration with image-text data
#755 opened Jan 9, 2026 by Edwardf0t1 • Draft
2
Svdquant huggingface checkpoint export support
#754 opened Jan 9, 2026 by sychen52 Loading…
1
Remove quantization_config in config.json from original deepseek models
#753 opened Jan 9, 2026 by Edwardf0t1 Loading…
1
[draft] bug for MoE distributed parallelism
#752 opened Jan 8, 2026 by realAsma • Draft
9
Fix Qwen3 recipe and update autoquant example cmd
#749 opened Jan 8, 2026 by meenchen • Draft
2
Top-K KL Divergence loss
#747 opened Jan 8, 2026 by AAnoosheh Loading…
@AAnoosheh
2
Feat: Context Parallel for Eagle3 Training
#745 opened Jan 8, 2026 by h-guo18 Loading…
@h-guo18
2
Support exclude module for exporting mcore models
#743 opened Jan 7, 2026 by meenchen Loading…
1
Bump the pip group across 2 directories with 2 updates dependencies Pull requests that update a dependency file python Pull requests that update python code
#737 opened Jan 5, 2026 by dependabot bot Loading…
1
Add support for MXFP8 PTQ
#736 opened Jan 5, 2026 by danisereb Loading…
25
Add score averaging and convergence early stop
#734 opened Dec 30, 2025 by CedricHwong Loading…
3
[5725362] AutoCast Fixes for models with external data
#731 opened Dec 28, 2025 by galagam • Draft
3
Fix MSE calibration distributed amax sync and add multi‑GPU test
#730 opened Dec 26, 2025 by CedricHwong Loading…
2
Patch DeepSeek V3 config to add missing qk_head_dim attribute if needed
#723 opened Dec 23, 2025 by Edwardf0t1 Loading…
2
Fix AWQ export when quantization of some layers are disabled
#721 opened Dec 22, 2025 by meenchen Loading…
@meenchen
1
Add NAS to Minitron pruning for parameter based auto-pruning
#720 opened Dec 22, 2025 by kevalmorabia97 Loading…
10
[5750013][5591945][5360813]: AutoCast standalone implementation for type inference
#719 opened Dec 22, 2025 by galagam Loading…
23
Feat: DeepseekV3 eagle
#715 opened Dec 20, 2025 by h-guo18 • Draft
2
Integrate Automated QDQ placement tool - Part 4
#704 opened Dec 17, 2025 by willg-nv Loading…
3
Integrate Automated QDQ placement tool - Part 3
#703 opened Dec 17, 2025 by willg-nv Loading…
10
Integrate Automated QDQ placement tool - Part 2
#702 opened Dec 17, 2025 by willg-nv Loading…
30
Integrate Automated QDQ placement tool - Part 1
#701 opened Dec 17, 2025 by willg-nv Loading…
73
Refactor: Clean up EAGLE training dataset preparation
#684 opened Dec 12, 2025 by benchislett Loading…
1
ProTip! Add no:assignee to see everything that’s not assigned.