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 }}
trailaptrinh
/
verl
Public
forked from
verl-project/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
main
User selector
All users
All time
Commit history
Commits on Feb 8, 2025
[ckpt] feat: integrate checkpoint resume in RL ray trainer (#222)
Show description for 5a400bf
PeterSH6
authored
5a400bf
View commit details
Copy full SHA for 5a400bf
Browse repository at this point
Fix typo tips in bash sft. (#226)
Show description for 62a065b
湛露先生
authored
62a065b
View commit details
Copy full SHA for 62a065b
Browse repository at this point
Memory efficiency improvement to logprobs_from_logits_v2 (#220)
Show description for 4b51624
tyler-romero
authored
4b51624
View commit details
Copy full SHA for 4b51624
Browse repository at this point
Commits on Feb 7, 2025
[TRACKING] feat: Integrate SwanLab for experiment tracking with online/offline mode and local dashboard support (#218)
Show description for 958a326
ShaohonChen
authored
958a326
View commit details
Copy full SHA for 958a326
Browse repository at this point
[rollout]: fix incorrect response_attention_mask in vLLM rollout (#213)
Show description for 3140cc2
kinman0224
authored
3140cc2
View commit details
Copy full SHA for 3140cc2
Browse repository at this point
[misc] feat: add ckpt manager in utils (#216)
Show description for 27484a7
PeterSH6
authored
27484a7
View commit details
Copy full SHA for 27484a7
Browse repository at this point
Commits on Feb 6, 2025
Create scorecard.yml for security scan (#215)
Show description for ee23b7b
willem-bd
authored
ee23b7b
View commit details
Copy full SHA for ee23b7b
Browse repository at this point
example: switch the default model ckpt for Megatron, add wandb logs (#210)
Show description for ced8ecb
eric-haibin-lin
and
Your Name
authored
ced8ecb
View commit details
Copy full SHA for ced8ecb
Browse repository at this point
docs: simple use name verl. add meetup info
eric-haibin-lin
authored
22d56a8
View commit details
Copy full SHA for 22d56a8
Browse repository at this point
Commits on Feb 5, 2025
[misc] fix: load and offload in compute log prob (#208)
Show description for 6872dbe
PeterSH6
authored
6872dbe
View commit details
Copy full SHA for 6872dbe
Browse repository at this point
[CI] feat: make the digit completion ci use fsdp's ppo_config (#206)
Show description for 89ba48e
PeterSH6
authored
89ba48e
View commit details
Copy full SHA for 89ba48e
Browse repository at this point
[misc] refactor: refactor config, add grpo ci (#204)
Show description for ac9d246
vermouth1992
authored
ac9d246
View commit details
Copy full SHA for ac9d246
Browse repository at this point
Update README.md (#203)
vermouth1992
authored
ce956cc
View commit details
Copy full SHA for ce956cc
Browse repository at this point
assert to make sure flash-attn>=2.4.3 (#202)
Show description for 49913bd
bebetterest
authored
49913bd
View commit details
Copy full SHA for 49913bd
Browse repository at this point
fix critic save error (#199)
Show description for 4669ab9
WeiXiongUST
authored
4669ab9
View commit details
Copy full SHA for 4669ab9
Browse repository at this point
docs: fixed link in gsm8k_example.rst (#200)
Show description for ddfc04e
jfncs
and
jaysonfrancis
authored
ddfc04e
View commit details
Copy full SHA for ddfc04e
Browse repository at this point
Commits on Feb 4, 2025
Call wandb.finish when the tracker is destructed if wandb is in use (#191)
Show description for 483fa8a
TonyLianLong
authored
483fa8a
View commit details
Copy full SHA for 483fa8a
Browse repository at this point
Remove unused variable in gsm8k preprocessing code (#193)
nch0w
authored
4d420fe
View commit details
Copy full SHA for 4d420fe
Browse repository at this point
fix link in quickstart.rst (#192)
Show description for 686a9c3
jfncs
and
jaysonfrancis
authored
686a9c3
View commit details
Copy full SHA for 686a9c3
Browse repository at this point
Commits on Feb 3, 2025
docs: Add LigerKernel performance tuning documentation (#178)
Show description for 3fe77fa
3 people
authored
3fe77fa
View commit details
Copy full SHA for 3fe77fa
Browse repository at this point
docs: update ray_trainer.rst (#187)
Show description for 13762f4
eltociear
authored
13762f4
View commit details
Copy full SHA for 13762f4
Browse repository at this point
megatron: fix config error and add compute log prob interface (#186)
eric-haibin-lin
authored
818e4de
View commit details
Copy full SHA for 818e4de
Browse repository at this point
docs: update readme with links to examples
eric-haibin-lin
authored
fbc8fe8
View commit details
Copy full SHA for fbc8fe8
Browse repository at this point
Commits on Feb 2, 2025
exchange the mini_batch_size calculation logic (#183)
chujiezheng
authored
6e003c0
View commit details
Copy full SHA for 6e003c0
Browse repository at this point
Commits on Feb 1, 2025
data: fix the math dataset source (#175)
Show description for 677e120
eric-haibin-lin
authored
677e120
View commit details
Copy full SHA for 677e120
Browse repository at this point
[misc] fix: grpo kl loss should be add when do minimization (#179)
Show description for a65c915
PeterSH6
authored
a65c915
View commit details
Copy full SHA for a65c915
Browse repository at this point
Commits on Jan 31, 2025
docs: add twitter link to readme
eric-haibin-lin
authored
38ac525
View commit details
Copy full SHA for 38ac525
Browse repository at this point
[feat, SFT] Support LigerKernel for SFT (#173)
xingyaoww
authored
25fc194
View commit details
Copy full SHA for 25fc194
Browse repository at this point
validate `use_remove_padding` when applying sequence parallelism (#153)
chujiezheng
authored
fb3793a
View commit details
Copy full SHA for fb3793a
Browse repository at this point
fix bug:fix checkpoint save with existing dirs (#174)
Show description for 679798c
dignfei
and
eric-haibin-lin
authored
679798c
View commit details
Copy full SHA for 679798c
Browse repository at this point
Commits on Jan 30, 2025
docs: add split placement to readme
eric-haibin-lin
authored
b6068ec
View commit details
Copy full SHA for b6068ec
Browse repository at this point
Allow users to pass in custom compute_score function (#162)
Show description for ce862ce
corbt
authored
ce862ce
View commit details
Copy full SHA for ce862ce
Browse repository at this point
fix: typo (explanation) (#167)
emergenz
authored
41b7c58
View commit details
Copy full SHA for 41b7c58
Browse repository at this point
fix: typo (#166)
emergenz
authored
e7fd415
View commit details
Copy full SHA for e7fd415
Browse repository at this point
[Liger-kernel] Add an option to use `_apply_liger_kernel_to_instance()` to load model (#133)
Show description for dd41877
hongpeng-guo
authored
dd41877
View commit details
Copy full SHA for dd41877
Browse repository at this point
Previous
Next
You can’t perform that action at this time.