Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Type
/
to search
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
Uh oh!
There was an error while loading.
Please reload this page
.
NVIDIA
/
Model-Optimizer
Public
Notifications
You must be signed in to change notification settings
Fork
539
Star
3.4k
Code
Issues
84
Pull requests
258
Actions
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Security and quality
Insights
Add Qwen-Image DMD2 QAT and PEFT-backed SVDQuant
- #2068
#2068
Closed
jingyu-ml
wants to merge 26 commits into
NVIDIA:main
NVIDIA/Model-Optimizer:main
from
jingyu-ml:feature/qwen-image-dmd2-qat
jingyu-ml/Model-Optimizer:feature/qwen-image-dmd2-qat
Copy head branch name to clipboard
Conversation
Commits
26
(26)
Checks
Files changed
Closed
Add Qwen-Image DMD2 QAT and PEFT-backed SVDQuant
#2068
jingyu-ml
wants to merge 26 commits into
NVIDIA:main
NVIDIA/Model-Optimizer:main
from
jingyu-ml:feature/qwen-image-dmd2-qat
jingyu-ml/Model-Optimizer:feature/qwen-image-dmd2-qat
Copy head branch name to clipboard
Commits
Commits on Jun 11, 2026
Add Qwen-Image registration to diffusers quantization example
Show description for 99a0444
jingyu-ml
and
claude
committed
99a0444
View commit details
Copy full SHA for 99a0444
Browse repository at this point
Commits on Jun 12, 2026
Qwen-Image SVDQuant: block-range recipe, AWQ-style diffusers export, harness
Show description for e0c7910
jingyu-ml
and
claude
committed
e0c7910
View commit details
Copy full SHA for e0c7910
Browse repository at this point
Qwen-Image SVDQuant: fix export/recipe defects, add Qwen QKV fusion + tests
Show description for 6718e72
jingyu-ml
and
claude
committed
6718e72
View commit details
Copy full SHA for 6718e72
Browse repository at this point
Qwen-Image SVDQuant: add export/fusion/promotion tests; drop plan terminology
Show description for 8e3b3ed
jingyu-ml
and
claude
committed
8e3b3ed
View commit details
Copy full SHA for 8e3b3ed
Browse repository at this point
Qwen-Image SVDQuant: offline tiny Qwen fixture + e2e export test
Show description for 027a5e2
jingyu-ml
and
claude
committed
027a5e2
View commit details
Copy full SHA for 027a5e2
Browse repository at this point
Qwen-Image SVDQuant: offline tokenizer, stronger export test, drop Step comments
Show description for a511058
jingyu-ml
and
claude
committed
a511058
View commit details
Copy full SHA for a511058
Browse repository at this point
Qwen-Image SVDQuant: fix misplaced parametrize decorator + tighten export test
Show description for a6a3d59
jingyu-ml
and
claude
committed
a6a3d59
View commit details
Copy full SHA for a6a3d59
Browse repository at this point
Qwen-Image SVDQuant: fix stale tiny-fixture tokenizer docstring
Show description for 1cfe0b3
jingyu-ml
and
claude
committed
1cfe0b3
View commit details
Copy full SHA for 1cfe0b3
Browse repository at this point
Qwen-Image SVDQuant: add immutability + negative-loading tests; fix stale docs
Show description for 789f4ef
jingyu-ml
and
claude
committed
789f4ef
View commit details
Copy full SHA for 789f4ef
Browse repository at this point
Qwen-Image SVDQuant: drop invalid txt_seq_lens dummy kwarg + signature-gate
Show description for 521cda0
jingyu-ml
and
claude
committed
521cda0
View commit details
Copy full SHA for 521cda0
Browse repository at this point
Qwen-Image SVDQuant: remove promoted export buffers from live module after export
Show description for d776ffb
jingyu-ml
and
claude
committed
d776ffb
View commit details
Copy full SHA for d776ffb
Browse repository at this point
Qwen-Image diffusers PTQ: fix 5 execution-surfaced bugs (fp8/nvfp4/svdquant)
Show description for c2250cb
jingyu-ml
and
claude
committed
c2250cb
View commit details
Copy full SHA for c2250cb
Browse repository at this point
Qwen-Image: drop operator-specific quantization harness from the example
Show description for fb23155
jingyu-ml
and
claude
committed
fb23155
View commit details
Copy full SHA for fb23155
Browse repository at this point
Qwen-Image: consolidate tests into the shared diffusers export suite
Show description for 80e2244
jingyu-ml
and
claude
committed
80e2244
View commit details
Copy full SHA for 80e2244
Browse repository at this point
Qwen-Image: add a fast CPU test for the diffusers SVDQuant export promotion
Show description for 9b472b2
jingyu-ml
and
claude
committed
9b472b2
View commit details
Copy full SHA for 9b472b2
Browse repository at this point
Commits on Jun 14, 2026
Merge branch 'main' into feature/qwen-image-svdquant-nvfp4
jingyu-ml
authored
4dff6d5
View commit details
Copy full SHA for 4dff6d5
Browse repository at this point
Commits on Jun 15, 2026
Merge branch 'main' into feature/qwen-image-svdquant-nvfp4
jingyu-ml
authored
31db239
View commit details
Copy full SHA for 31db239
Browse repository at this point
Commits on Jun 23, 2026
Qwen-Image diffusers PTQ: address review feedback (cleanup safety, rank check, imports)
Show description for 4a92a69
jingyu-ml
and
claude
committed
4a92a69
View commit details
Copy full SHA for 4a92a69
Browse repository at this point
Merge branch 'main' into feature/qwen-image-svdquant-nvfp4
Show description for 6e3392b
jingyu-ml
and
claude
committed
6e3392b
View commit details
Copy full SHA for 6e3392b
Browse repository at this point
Qwen-Image: simplify unavailable-pipeline error in PipelineManager
Show description for 2ad6a8f
jingyu-ml
and
claude
committed
2ad6a8f
View commit details
Copy full SHA for 2ad6a8f
Browse repository at this point
Commits on Jun 24, 2026
Qwen-Image: drop the optional --sanity-image-path inference check
Show description for 4bfe484
jingyu-ml
and
claude
committed
4bfe484
View commit details
Copy full SHA for 4bfe484
Browse repository at this point
Qwen-Image: move onnx_utils import back to module top in quantize.py
Show description for 2269e96
jingyu-ml
and
claude
committed
2269e96
View commit details
Copy full SHA for 2269e96
Browse repository at this point
Qwen-Image: fix code-quality CI (mypy dict-item, ruff format/lint)
Show description for daf6d0f
jingyu-ml
and
claude
committed
daf6d0f
View commit details
Copy full SHA for daf6d0f
Browse repository at this point
Commits on Jun 25, 2026
Add Qwen-Image DMD2 PTQ support; save quantizer state (amax) without weights
Show description for a689f31
jingyu-ml
and
claude
committed
a689f31
View commit details
Copy full SHA for a689f31
Browse repository at this point
Commits on Jul 1, 2026
Add Qwen-Image-Edit DMD2 training and QAT support
jingyu-ml
committed
f7a9140
View commit details
Copy full SHA for f7a9140
Browse repository at this point
Commits on Aug 5, 2026
Merge remote-tracking branch 'origin/main' into feature/qwen-image-dmd2-qat
Show description for 3d3cf76
jingyu-ml
committed
3d3cf76
View commit details
Copy full SHA for 3d3cf76
Browse repository at this point
You can’t perform that action at this time.
