Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
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 }}
modelscope
twinkle
Repository navigation
Code
Issues
3
(3)
Pull requests
27
(27)
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
10
(10)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
27
(27)
Closed
340
(340)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[v5] 减少 FSDP2 累积与 vLLM 权重发布开销
#390
·
qychen2001
opened
Nov 17, 2026
Collaborator
·
·
fix(kernel): align fused entropy backward with native rounding
#389
·
diaochengxi
opened
Nov 17, 2026
Contributor
·
·
fix(server): preserve task loaders and checkpoint resume state
#387
·
Yunnglin
opened
Nov 16, 2026
Collaborator
·
·
5
Add the single-device Qwen3-TTS LoRA cookbook
#384
·
Wallbreazzz
opened
Nov 12, 2026
·
·
Add the Qwen3-TTS dual-channel input processor
#383
·
Wallbreazzz
opened
Nov 12, 2026
·
·
Register the Qwen3-TTS residual codebook loss
#382
·
Wallbreazzz
opened
Nov 12, 2026
·
·
Add the Qwen3-TTS two-stage training forward patch
#381
·
Wallbreazzz
opened
Nov 12, 2026
·
·
Defer pretrained architecture resolution to the model loader
#380
·
Wallbreazzz
opened
Nov 12, 2026
·
·
Adaptive mopd weight
#377
·
indigoRM
opened
Nov 12, 2026
·
4 tasks
·
·
fix(auto): detect the accelerator before starting the training server
#371
·
li-lizhe
opened
Nov 7, 2026
Contributor
·
1 of 4 tasks
·
·
1
feat(model): move DP balancing into TrainableModel, enabled by default
#367
·
lincq2000
opened
Nov 3, 2026
Collaborator
·
2 of 4 tasks
·
·
RL续训
#340
·
indigoRM
opened
Oct 26, 2026
·
1 of 4 tasks
·
·
fix(loss): compute the IPO loss as in Eq. 17 of the IPO paper
#327
·
flyingdoubleG
opened
Oct 21, 2026
Contributor
·
2 of 4 tasks
·
·
1
fix(loss): truncate the CISPO IS weight at 1 + epsilon_high
#326
·
flyingdoubleG
opened
Oct 21, 2026
Contributor
·
2 of 4 tasks
·
·
fix: restore local optimizer state without distributed broadcast
#317
·
Liuchenbing-2026
opened
Oct 14, 2026
Contributor
·
1 of 4 tasks
·
·
1
fix: update on complete gradient accumulation boundaries
#316
·
Liuchenbing-2026
opened
Oct 14, 2026
Contributor
·
1 of 4 tasks
·
·
1
feat: add native typed decision training components
#314
·
Liuchenbing-2026
opened
Oct 14, 2026
Contributor
·
3 of 4 tasks
·
·
feat: add StartLux decision LoRA training on Ascend
#305
·
Liuchenbing-2026
opened
Oct 12, 2026
Contributor
·
4 tasks done
·
·
feat: add Intern-Decision text training cookbook on Ascend
#295
·
Liuchenbing-2026
opened
Oct 8, 2026
Contributor
·
2 of 3 tasks
·
·
fix: weight PPO token-mean micro-batches by valid tokens
#292
·
taking-lying-flat
opened
Sep 20, 2026
·
1 of 4 tasks
·
·
fix: detach probability weights in DFT loss
#291
·
taking-lying-flat
opened
Sep 20, 2026
·
1 of 4 tasks
·
·
fix: avoid duplicate gradient norm reduction in pure DDP
#290
·
taking-lying-flat
opened
Sep 20, 2026
·
1 of 4 tasks
·
·
[feature]reward_loop
#284
·
doctorMcy
opened
Sep 15, 2026
·
3 tasks
·
·
feat(rl): add SAO synchronous training baseline with skip-observation GAE, DIS policy loss and value critic ```
#269
·
xxyyrr598
opened
Aug 19, 2026
Contributor
·
·
6
add java client
#268
·
ljhandhya
opened
Aug 18, 2026
·
3 tasks
·
·
Previous
1
2
Next
You can’t perform that action at this time.