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 }}
DaoyuanLi2816
/
mini-verl
Public
Notifications
You must be signed in to change notification settings
Fork
20
Star
79
Code
Issues
2
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Breadcrumbs
History for
mini-verl
tests
unit
on
main
User selector
All users
All time
Commit history
Commits on Aug 14, 2026
Mark PG loss tests as torch-optional
DaoyuanLi2816
committed
6119ed5
View commit details
Copy full SHA for 6119ed5
View code at this point
Browse repository at this point
Record measured PG profile evidence
DaoyuanLi2816
committed
9b502e0
View commit details
Copy full SHA for 9b502e0
View code at this point
Browse repository at this point
Add pinned sampled-k1 OPD profile
DaoyuanLi2816
committed
6fe3083
View commit details
Copy full SHA for 6fe3083
View code at this point
Browse repository at this point
Add versioned compatibility profile registry (#79)
DaoyuanLi2816
authored
8fbaefb
View commit details
Copy full SHA for 8fbaefb
View code at this point
Browse repository at this point
Align verl OPD documentation with runtime truth (#76)
Show description for 729b364
DaoyuanLi2816
authored
729b364
View commit details
Copy full SHA for 729b364
View code at this point
Browse repository at this point
Repair verl OPD semantic contracts (#75)
DaoyuanLi2816
authored
8cb670c
View commit details
Copy full SHA for 8cb670c
View code at this point
Browse repository at this point
Commits on Aug 13, 2026
Prepare the v0.9.0 release
DaoyuanLi2816
committed
6f34cc0
View commit details
Copy full SHA for 6f34cc0
View code at this point
Browse repository at this point
Bind the final OPD workload evidence
DaoyuanLi2816
committed
7a36f59
View commit details
Copy full SHA for 7a36f59
View code at this point
Browse repository at this point
Publish the RTX 4080 OPD developer workload
DaoyuanLi2816
committed
3b30250
View commit details
Copy full SHA for 3b30250
View code at this point
Browse repository at this point
Define exact real-model resume equivalence
DaoyuanLi2816
committed
f61f760
View commit details
Copy full SHA for f61f760
View code at this point
Browse repository at this point
Materialize launchable verl OPD bundles (#71)
Show description for 7e85824
DaoyuanLi2816
authored
7e85824
View commit details
Copy full SHA for 7e85824
View code at this point
Browse repository at this point
Add bounded CUDA hardware probe (#70)
DaoyuanLi2816
authored
aad824d
View commit details
Copy full SHA for aad824d
View code at this point
Browse repository at this point
Bind runs to immutable execution plans (#69)
DaoyuanLi2816
authored
0697c69
View commit details
Copy full SHA for 0697c69
View code at this point
Browse repository at this point
Add verl-style override workflow (#68)
DaoyuanLi2816
authored
e70eba3
View commit details
Copy full SHA for e70eba3
View code at this point
Browse repository at this point
Advance development to 0.9.0.dev0 (#67)
DaoyuanLi2816
authored
5238c3e
View commit details
Copy full SHA for 5238c3e
View code at this point
Browse repository at this point
Make the verl OPD workflow product-first (#65)
Show description for 8d3ebb2
DaoyuanLi2816
authored
8d3ebb2
View commit details
Copy full SHA for 8d3ebb2
View code at this point
Browse repository at this point
Commits on Aug 12, 2026
Add pure OPD bridge round trip and finalize v0.8.0
DaoyuanLi2816
committed
4fe229e
View commit details
Copy full SHA for 4fe229e
View code at this point
Browse repository at this point
Preserve legacy cycle metric contracts
DaoyuanLi2816
committed
5dc5473
View commit details
Copy full SHA for 5dc5473
View code at this point
Browse repository at this point
Publish measured RTX 4080 OPD quickstart
DaoyuanLi2816
committed
eeb257d
View commit details
Copy full SHA for eeb257d
View code at this point
Browse repository at this point
Add verl-style OPD plan and run workflow
DaoyuanLi2816
committed
33ddbf1
View commit details
Copy full SHA for 33ddbf1
View code at this point
Browse repository at this point
Satisfy conformance test lint
DaoyuanLi2816
committed
ffbeb97
View commit details
Copy full SHA for ffbeb97
View code at this point
Browse repository at this point
Keep conformance tests collection-safe
DaoyuanLi2816
committed
2c48d79
View commit details
Copy full SHA for 2c48d79
View code at this point
Browse repository at this point
Conform forward top-k loss with verl v0.8
DaoyuanLi2816
committed
518b8d0
View commit details
Copy full SHA for 518b8d0
View code at this point
Browse repository at this point
Keep torch marker collection-safe
DaoyuanLi2816
committed
db2d843
View commit details
Copy full SHA for db2d843
View code at this point
Browse repository at this point
Mark prompt rollout tests as torch-dependent
DaoyuanLi2816
committed
c9aa397
View commit details
Copy full SHA for c9aa397
View code at this point
Browse repository at this point
Add first-class Parquet prompt OPD runtime
DaoyuanLi2816
committed
7d140c8
View commit details
Copy full SHA for 7d140c8
View code at this point
Browse repository at this point
Add typed verl v0.8 OPD config compiler
Show description for 87bea41
DaoyuanLi2816
authored
87bea41
View commit details
Copy full SHA for 87bea41
View code at this point
Browse repository at this point
Release v0.7.1 product correction
Show description for 830a4ca
DaoyuanLi2816
authored
830a4ca
View commit details
Copy full SHA for 830a4ca
View code at this point
Browse repository at this point
Commits on Aug 11, 2026
Release v0.7.0 early-stop evidence (#53)
Show description for 1488229
DaoyuanLi2816
authored
1488229
View commit details
Copy full SHA for 1488229
View code at this point
Browse repository at this point
Commits on Aug 10, 2026
v0.7.0 preregistration: freeze the study and record a preregistered checkpoint-selection failure (#51)
Show description for c50aa93
DaoyuanLi2816
authored
c50aa93
View commit details
Copy full SHA for c50aa93
View code at this point
Browse repository at this point
Commits on Aug 9, 2026
v0.7.0 external benchmarks: pinned endpoints, judges and the frozen evaluation suite (#50)
Show description for 08dc3c3
DaoyuanLi2816
authored
08dc3c3
View commit details
Copy full SHA for 08dc3c3
View code at this point
Browse repository at this point
Commits on Aug 8, 2026
v0.7.0 foundation: refuse redirected bundles and bind sidecars to their dataset (#49)
Show description for 0be43b0
DaoyuanLi2816
authored
0be43b0
View commit details
Copy full SHA for 0be43b0
View code at this point
Browse repository at this point
Commits on Aug 6, 2026
Strip a UTF-8 byte-order mark before parsing a reward scaffold (#48)
Show description for 0bd1946
DaoyuanLi2816
authored
0bd1946
View commit details
Copy full SHA for 0bd1946
View code at this point
Browse repository at this point
Close the v0.6.3 reward-verifier, trust-boundary, sidecar and streaming gaps (#46)
Show description for 005a454
DaoyuanLi2816
authored
005a454
View commit details
Copy full SHA for 005a454
View code at this point
Browse repository at this point
Commits on Aug 5, 2026
v0.6.3 security, artifact integrity and release-state hardening (#45)
Show description for b769251
DaoyuanLi2816
authored
b769251
View commit details
Copy full SHA for b769251
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.