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
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 }}
WongLiAtom
/
mini-verl
Public
forked from
DaoyuanLi2816/mini-verl
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Branch selector
v0.2.0
User selector
All users
Datepicker
All time
Commit history
Commits on Jul 29, 2026
Sync final v0.2 release state (#7)
DaoyuanLi2816
authored
6092706
View commit details
Copy full SHA for 6092706
Browse repository at this point
Finalize v0.2 offline and release contracts (#6)
Show description for 4287682
DaoyuanLi2816
authored
4287682
View commit details
Copy full SHA for 4287682
Browse repository at this point
Commits on Jul 28, 2026
Harden trainer lifecycle and v0.2 release provenance (#5)
Show description for caed62f
DaoyuanLi2816
authored
caed62f
View commit details
Copy full SHA for caed62f
Browse repository at this point
Merge pull request #4 from DaoyuanLi2816/v0.2-protocol-aligned-opd
Show description for 4859531
DaoyuanLi2816
authored
4859531
View commit details
Copy full SHA for 4859531
Browse repository at this point
Publish protocol-teacher GPU benchmark
DaoyuanLi2816
committed
925e765
View commit details
Copy full SHA for 925e765
Browse repository at this point
Honor disabled periodic evaluation
DaoyuanLi2816
committed
3dafd5f
View commit details
Copy full SHA for 3dafd5f
Browse repository at this point
Pin complete upload-artifact SHA
DaoyuanLi2816
committed
e5e80b1
View commit details
Copy full SHA for e5e80b1
Browse repository at this point
Harden OPD protocol and benchmark provenance
DaoyuanLi2816
committed
5b11caf
View commit details
Copy full SHA for 5b11caf
Browse repository at this point
Commits on Jul 27, 2026
Make every written artifact byte-identical across platforms
Show description for 3383f2b
DaoyuanLi2816
committed
3383f2b
View commit details
Copy full SHA for 3383f2b
Browse repository at this point
Normalize line endings to LF and pin them with .gitattributes
Show description for 4a91a1f
DaoyuanLi2816
committed
4a91a1f
View commit details
Copy full SHA for 4a91a1f
Browse repository at this point
Fix three defects the first public CI run exposed
Show description for 9c29f60
DaoyuanLi2816
committed
9c29f60
View commit details
Copy full SHA for 9c29f60
Browse repository at this point
Import Result from typer, not click
Show description for 87d4ca2
DaoyuanLi2816
committed
87d4ca2
View commit details
Copy full SHA for 87d4ca2
Browse repository at this point
Refresh PROJECT_STATE with the final gates, results and defect log
Show description for efa8f1a
DaoyuanLi2816
committed
efa8f1a
View commit details
Copy full SHA for efa8f1a
Browse repository at this point
Write null, not NaN, for undefined metrics
Show description for 6cebfda
DaoyuanLi2816
committed
6cebfda
View commit details
Copy full SHA for 6cebfda
Browse repository at this point
Publish the two-seed CPU parity benchmark and say what it cannot show
Show description for ce61dff
DaoyuanLi2816
committed
ce61dff
View commit details
Copy full SHA for ce61dff
Browse repository at this point
Record the negative benchmark result and the attribution script in the changelog
Show description for 58dfd17
DaoyuanLi2816
committed
58dfd17
View commit details
Copy full SHA for 58dfd17
Browse repository at this point
Model log1mexp cancellation in the data-processing-inequality property
Show description for 67c1523
DaoyuanLi2816
committed
67c1523
View commit details
Copy full SHA for 67c1523
Browse repository at this point
Verify the built distribution in clean environments and align doctor output
Show description for 88ec337
DaoyuanLi2816
committed
88ec337
View commit details
Copy full SHA for 88ec337
Browse repository at this point
Report the matched-budget benchmark honestly: on-policy distillation lost
Show description for da987d9
DaoyuanLi2816
committed
da987d9
View commit details
Copy full SHA for da987d9
Browse repository at this point
Make the log1mexp clamp dtype-aware and put ENVIRONMENT_ERROR to work
Show description for f2f89da
DaoyuanLi2816
committed
f2f89da
View commit details
Copy full SHA for f2f89da
Browse repository at this point
Make the demo honest about what it proves, and tune the toy recipe until it learns
Show description for 38e6dd6
DaoyuanLi2816
committed
38e6dd6
View commit details
Copy full SHA for 38e6dd6
Browse repository at this point
Lint the newly tracked models package and add the privileged-context benchmark arm
Show description for d40942e
DaoyuanLi2816
committed
d40942e
View commit details
Copy full SHA for d40942e
Browse repository at this point
Add README, banner, docs, ADRs, CI, examples and OSS metadata
Show description for 37781ef
DaoyuanLi2816
committed
37781ef
View commit details
Copy full SHA for 37781ef
Browse repository at this point
Add integration, property and GPU tests; make resume exact
Show description for 896094e
DaoyuanLi2816
committed
896094e
View commit details
Copy full SHA for 896094e
Browse repository at this point
Harden the CLI, config and reporting against defects found by the test suite
Show description for 64aa3c0
DaoyuanLi2816
committed
64aa3c0
View commit details
Copy full SHA for 64aa3c0
Browse repository at this point
Implement miniVERL v0.1.0 core: numerics, environments, backends, trainer, CLI
Show description for 3968446
DaoyuanLi2816
committed
3968446
View commit details
Copy full SHA for 3968446
Browse repository at this point
You can’t perform that action at this time.