René's URL Explorer Experiment


Title: GitHub - NovaSky-AI/verl-fork

Open Graph Title: GitHub - NovaSky-AI/verl-fork

X Title: GitHub - NovaSky-AI/verl-fork

Description: Contribute to NovaSky-AI/verl-fork development by creating an account on GitHub.

Open Graph Description: Contribute to NovaSky-AI/verl-fork development by creating an account on GitHub.

X Description: Contribute to NovaSky-AI/verl-fork development by creating an account on GitHub.

Mail addresses
haibin.lin@bytedance.com

Opengraph URL: https://github.com/NovaSky-AI/verl-fork

X: @github

direct link

Domain: patch-diff.githubusercontent.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:b9613630-d355-db12-4bbb-8c5f3dffa14a
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idAB50:B3C06:B4E5C7:E4CDC7:697E7A07
html-safe-nonce9b7a8bbaac52be62ccd32dd521ba95f861875098c8dfa4f7e9c5ca7c7dffb28e
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJBQjUwOkIzQzA2OkI0RTVDNzpFNENEQzc6Njk3RTdBMDciLCJ2aXNpdG9yX2lkIjoiMTI1Mzk1MzI1MDQ0MTE5ODA4NyIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9
visitor-hmac2017de8e9c8dffa5a92d92c4674d961e4acc1826d003d4e855bf2665c6a4664d
hovercard-subject-tagrepository:1104904776
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/NovaSky-AI/verl-fork
twitter:imagehttps://opengraph.githubassets.com/927646edea91bce2d7ae46951aa5dafc707ab6c1ee84b622f08656fd8322498c/NovaSky-AI/verl-fork
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/927646edea91bce2d7ae46951aa5dafc707ab6c1ee84b622f08656fd8322498c/NovaSky-AI/verl-fork
og:image:altContribute to NovaSky-AI/verl-fork development by creating an account on GitHub.
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
None60279d4097367e16897439d16d6bbe4180663db828c666eeed2656988ffe59f6
turbo-cache-controlno-preview
go-importgithub.com/NovaSky-AI/verl-fork git https://github.com/NovaSky-AI/verl-fork.git
octolytics-dimension-user_id194174999
octolytics-dimension-user_loginNovaSky-AI
octolytics-dimension-repository_id1104904776
octolytics-dimension-repository_nwoNovaSky-AI/verl-fork
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id1104904776
octolytics-dimension-repository_network_root_nwoNovaSky-AI/verl-fork
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release7c85641c598ad130c74f7bcc27f58575cac69551
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#start-of-content
https://patch-diff.githubusercontent.com/
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FNovaSky-AI%2Fverl-fork
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub SparkBuild and deploy intelligent appshttps://github.com/features/spark
GitHub ModelsManage and compare promptshttps://github.com/features/models
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
GitHub SponsorsFund open source developershttps://github.com/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/accelerator
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FNovaSky-AI%2Fverl-fork
Sign up https://patch-diff.githubusercontent.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=NovaSky-AI%2Fverl-fork
Reloadhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Reloadhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Reloadhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
NovaSky-AI https://patch-diff.githubusercontent.com/NovaSky-AI
verl-forkhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FNovaSky-AI%2Fverl-fork
Fork 0 https://patch-diff.githubusercontent.com/login?return_to=%2FNovaSky-AI%2Fverl-fork
Star 0 https://patch-diff.githubusercontent.com/login?return_to=%2FNovaSky-AI%2Fverl-fork
Apache-2.0 license https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/LICENSE
0 stars https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/stargazers
0 forks https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/forks
Branches https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/branches
Tags https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tags
Activity https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/activity
Star https://patch-diff.githubusercontent.com/login?return_to=%2FNovaSky-AI%2Fverl-fork
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FNovaSky-AI%2Fverl-fork
Code https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Issues 0 https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/issues
Pull requests 5 https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/pulls
Actions https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/actions
Projects 0 https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/projects
Security 0 https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/security
Insights https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/pulse
Code https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Issues https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/issues
Pull requests https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/pulls
Actions https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/actions
Projects https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/projects
Security https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/security
Insights https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/pulse
Brancheshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/branches
Tagshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tags
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/branches
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tags
1,105 Commitshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/commits/main/
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/commits/main/
.geminihttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/.gemini
.geminihttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/.gemini
.githubhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/.github
.githubhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/.github
.vscodehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/.vscode
.vscodehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/.vscode
dockerhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/docker
dockerhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/docker
docshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/docs
docshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/docs
exampleshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/examples
exampleshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/examples
recipehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/recipe
recipehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/recipe
scriptshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/scripts
scriptshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/scripts
testshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/tests
testshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/tests
verlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/verl
verlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/tree/main/verl
.gitignorehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/.gitignore
.gitignorehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/.gitignore
.pre-commit-config.yamlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/.pre-commit-config.yaml
.pre-commit-config.yamlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/.pre-commit-config.yaml
.readthedocs.yamlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/.readthedocs.yaml
.readthedocs.yamlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/.readthedocs.yaml
CONTRIBUTING.mdhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/CONTRIBUTING.md
CONTRIBUTING.mdhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/CONTRIBUTING.md
LICENSEhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/LICENSE
LICENSEhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/LICENSE
Notice.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/Notice.txt
Notice.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/Notice.txt
README.mdhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/README.md
README.mdhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/README.md
pyproject.tomlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/pyproject.toml
pyproject.tomlhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/pyproject.toml
requirements-npu.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/requirements-npu.txt
requirements-npu.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/requirements-npu.txt
requirements.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/requirements.txt
requirements.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/requirements.txt
requirements_sglang.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/requirements_sglang.txt
requirements_sglang.txthttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/requirements_sglang.txt
setup.pyhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/setup.py
setup.pyhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/setup.py
READMEhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Contributinghttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Apache-2.0 licensehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
https://deepwiki.com/volcengine/verl
https://github.com/volcengine/verl/stargazers
https://twitter.com/verl_project
https://join.slack.com/t/verlgroup/shared_invite/zt-2w5p9o4c3-yy0x2Q56s_VlGLsJ93A6vA
https://arxiv.org/pdf/2409.19256
https://verl.readthedocs.io/en/latest/
https://raw.githubusercontent.com/eric-haibin-lin/verl-community/refs/heads/main/WeChat.JPG
https://private-user-images.githubusercontent.com/202069134/420340196-c42e675e-497c-4508-8bb9-093ad4d1f216.jpg?jwt=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3Njk4OTY3NTUsIm5iZiI6MTc2OTg5NjQ1NSwicGF0aCI6Ii8yMDIwNjkxMzQvNDIwMzQwMTk2LWM0MmU2NzVlLTQ5N2MtNDUwOC04YmI5LTA5M2FkNGQxZjIxNi5qcGc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjYwMTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI2MDEzMVQyMTU0MTVaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT03MzQ4NzM2NmEyZmIyMWM0ZDFiMWQzMjE2ZDQ5MzI2YjhjOWVlYmIwYmMyZWE2MjI2ZjgwZjI3ZjliOWM4ZDNhJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCJ9.3Tnv_-HBN7q3vTIUV-htvT_bY-NMFnwJDfsioTzO6HM
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#verl-volcano-engine-reinforcement-learning-for-llms
HybridFlow: A Flexible and Efficient RLHF Frameworkhttps://arxiv.org/abs/2409.19256v2
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#news
join ushttps://lu.ma/0ek2nyao
AWS AI Hours Singaporehttps://pages.awscloud.com/aws-ai-hours-sg.html#agenda
Agent for SWE meetuphttps://lu.ma/e498qhsi
DeepSeek-671b and Qwen3-236bhttps://verl.readthedocs.io/en/latest/perf/dpsk.html
PyTorch Day Chinahttps://www.lfasiallc.com/pytorch-day-china/
Seed-Thinking-v1.5https://github.com/ByteDance-Seed/Seed-Thinking-v1.5/blob/main/seed-thinking-v1.5.pdf
DAPOhttps://dapo-sia.github.io/
https://arxiv.org/pdf/2504.05118https://arxiv.org/pdf/2504.05118
https://arxiv.org/abs/2409.06957https://arxiv.org/abs/2409.06957
https://iclr.cc/virtual/2025/calendar?filter_events=Expo+Talk+Panel&filter_rooms=https://iclr.cc/virtual/2025/calendar?filter_events=Expo+Talk+Panel&filter_rooms=
https://open-foundation-model.github.io/https://open-foundation-model.github.io/
https://lu.ma/d23nyynmhttps://lu.ma/d23nyynm
https://github.com/eric-haibin-lin/verl-community/tree/main/iclr25https://github.com/eric-haibin-lin/verl-community/tree/main/iclr25
https://github.com/volcengine/verl/releases/https://github.com/volcengine/verl/releases/
https://tongyx361.github.io/blogs/posts/verl-intro/#/verl-flexible-and-efficient-rl-for-llmshttps://tongyx361.github.io/blogs/posts/verl-intro/#/verl-flexible-and-efficient-rl-for-llms
https://a2m.msup.com.cn/home/?aid=4488&city=shanghaihttps://a2m.msup.com.cn/home/?aid=4488&city=shanghai
https://paris2025.gosim.org/https://paris2025.gosim.org/
https://mp.weixin.qq.com/s/n77GibL2corAtQHtVEAzfghttps://mp.weixin.qq.com/s/n77GibL2corAtQHtVEAzfg
https://github.com/eric-haibin-lin/verl-community/blob/main/slides/verl-lmsys-meetup.pdfhttps://github.com/eric-haibin-lin/verl-community/blob/main/slides/verl-lmsys-meetup.pdf
https://lu.ma/ntjrr7ighttps://lu.ma/ntjrr7ig
Bytedance/NVIDIA/Anyscale Ray Meetuphttps://lu.ma/ji7atxux
https://team.doubao.com/zh/special/doubao_1_5_prohttps://team.doubao.com/zh/special/doubao_1_5_pro
herehttps://github.com/eric-haibin-lin/verl-community/blob/main/slides/Ray_Forward_2024_%E5%B7%AB%E9%94%A1%E6%96%8C.pdf
Post-training LLMs: From Algorithms to Infrastructurehttps://neurips.cc/Expo/Conferences/2024/workshop/100677
Slideshttps://github.com/eric-haibin-lin/verl-data/tree/neurips
videohttps://neurips.cc/Expo/Conferences/2024/workshop/100677
Youtube videohttps://www.youtube.com/watch?v=MrhMcXkXvJU&list=PLzTswPQNepXntmT8jr9WaNfqQ60QwW7-U&index=37
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#key-features
Qwen-3https://github.com/volcengine/verl/blob/main/examples/grpo_trainer/run_qwen3-8b.sh
PPOhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/ppo_trainer
GRPOhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/grpo_trainer
ReMaxhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/remax_trainer
REINFORCE++https://verl.readthedocs.io/en/latest/examples/config.html#algorithm
RLOOhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/rloo_trainer
PRIMEhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/recipe/prime
DAPOhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/recipe/dapo
DrGRPOhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/recipe/drgrpo
KL_Cov & Clip_Covhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/recipe/entropy
codinghttps://github.com/volcengine/verl/tree/main/recipe/dapo
multi-modal RLhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/grpo_trainer/run_qwen2_5_vl-7b.sh
Multi-turn with tool callinghttps://github.com/volcengine/verl/tree/main/examples/sglang_multiturn
Self-play preference optimization (SPPO)https://github.com/volcengine/verl/tree/main/recipe/sppo
sequence packinghttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh
sequence parallelismhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh
LoRAhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/sft/gsm8k/run_qwen_05_peft.sh
Liger-kernelhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh
expert parallelismhttps://github.com/volcengine/verl/pull/1467
LoRA RLhttps://verl.readthedocs.io/en/latest/advance/ppo_lora.html
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#upcoming-features-and-changes
verl-project/verl#2388https://github.com/verl-project/verl/issues/2388
verl-project/verl#1033https://github.com/verl-project/verl/issues/1033
verl-project/verl#1882https://github.com/verl-project/verl/issues/1882
Agent integrationhttps://github.com/volcengine/verl/tree/main/verl/experimental/agent_loop
verl-project/verl#2231https://github.com/verl-project/verl/pull/2231
verl-project/verl#2270https://github.com/verl-project/verl/discussions/2270
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#getting-started
Documentationhttps://verl.readthedocs.io/en/latest/index.html
Installationhttps://verl.readthedocs.io/en/latest/start/install.html
Quickstarthttps://verl.readthedocs.io/en/latest/start/quickstart.html
Programming Guidehttps://verl.readthedocs.io/en/latest/hybrid_flow.html
Tech Talkhttps://hcqnc.xetlk.com/sl/3vACOK
PPO in verlhttps://verl.readthedocs.io/en/latest/algo/ppo.html
GRPO in verlhttps://verl.readthedocs.io/en/latest/algo/grpo.html
Prepare Data for Post-Traininghttps://verl.readthedocs.io/en/latest/preparation/prepare_data.html
Implement Reward Function for Datasethttps://verl.readthedocs.io/en/latest/preparation/reward_function.html
PPO Example Architecturehttps://verl.readthedocs.io/en/latest/examples/ppo_code_architecture.html
Config Explanationhttps://verl.readthedocs.io/en/latest/examples/config.html
RL performance on coding, mathhttps://verl.readthedocs.io/en/latest/algo/baseline.html
PPO Ray Trainerhttps://verl.readthedocs.io/en/latest/workers/ray_trainer.html
PyTorch FSDP Backendhttps://verl.readthedocs.io/en/latest/workers/fsdp_workers.html
Megatron-LM Backendhttps://verl.readthedocs.io/en/latest/index.html
Add Models with the FSDP Backendhttps://verl.readthedocs.io/en/latest/advance/fsdp_extension.html
Add Models with the Megatron-LM Backendhttps://verl.readthedocs.io/en/latest/advance/megatron_extension.html
Multi-turn Rollout Supporthttps://verl.readthedocs.io/en/latest/sglang_multiturn/multiturn.html
Search Tool Integrationhttps://verl.readthedocs.io/en/latest/sglang_multiturn/search_tool_example.html
Sandbox Fusion Integrationhttps://verl.readthedocs.io/en/latest/examples/sandbox_fusion_example.html
Deployment using Separate GPU Resourceshttps://github.com/volcengine/verl/tree/main/examples/split_placement
Extend to Other RL(HF) algorithmshttps://verl.readthedocs.io/en/latest/advance/dpo_extension.html
Ray API design tutorialhttps://verl.readthedocs.io/en/latest/advance/placement.html
When Reasoning Models Break Tokenization: The Hidden Complexity of Multiturn Traininghttps://github.com/zhaochenyang20/Awesome-ML-SYS-Tutorial/blob/main/rlhf/verl/multi-turn/fast_tokenization/multiturn_tokenization_and_masking.md
verl deployment on AWS SageMakerhttps://medium.com/@kaige.yang0110/run-verl-on-sagemaker-using-4x8-l40s-gpus-8e6d5c3c61d3
verl x SGLang Multi-turn Code Walkthroughhttps://github.com/zhaochenyang20/Awesome-ML-SYS-Tutorial/blob/main/rlhf/verl/multi-turn/code-walk-through/readme_EN.md
Optimizing SGLang Memory Usage in verlhttps://hebiao064.github.io/rl-memory-management
SGLang, verl, OpenBMB and Tsinghua University: Pioneering End-to-End Multi-Turn RLHFhttps://github.com/zhaochenyang20/Awesome-ML-SYS-Tutorial/blob/main/rlhf/verl/multi-turn/verl-multiturn-rollout-Release.md
Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integrationhttps://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html
veMLP x verl ：玩转强化学习训练https://mp.weixin.qq.com/s/7nbqxk4knMGd-hQE9ls2tA
使用 verl 进行 GRPO 分布式强化学习训练最佳实践https://www.volcengine.com/docs/6459/1463942
HybridFlow verl 原文浅析https://github.com/zhaochenyang20/Awesome-ML-SYS-Tutorial/blob/main/rlhf/verl/readme.md
最高提升 20 倍吞吐量！豆包大模型团队发布全新 RLHF 框架，现已开源！https://team.doubao.com/en/blog/%E6%9C%80%E9%AB%98%E6%8F%90%E5%8D%8720%E5%80%8D%E5%90%9E%E5%90%90%E9%87%8F-%E8%B1%86%E5%8C%85%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9B%A2%E9%98%9F%E5%8F%91%E5%B8%83%E5%85%A8%E6%96%B0-rlhf-%E6%A1%86%E6%9E%B6-%E7%8E%B0%E5%B7%B2%E5%BC%80%E6%BA%90
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#performance-tuning-guide
performance tuning guidehttps://verl.readthedocs.io/en/latest/perf/perf_tuning.html
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#upgrade-to-vllm--v082
this documenthttps://github.com/volcengine/verl/blob/main/docs/README_vllm0.8.md
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#use-latest-sglang
this documenthttps://verl.readthedocs.io/en/latest/workers/sglang_worker.html
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#upgrade-to-fsdp2
verl-project/verl#1026https://github.com/verl-project/verl/pull/1026
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#amd-support-rocm-kernel
this documenthttps://github.com/volcengine/verl/blob/main/docs/amd_tutorial/amd_build_dockerfile_page.rst
this documenthttps://github.com/volcengine/verl/blob/main/docs/amd_tutorial/amd_vllm_page.rst
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#citation-and-acknowledgement
HybridFlow: A Flexible and Efficient RLHF Frameworkhttps://arxiv.org/abs/2409.19256v2
A Framework for Training Large Language Models for Code Generation via Proximal Policy Optimizationhttps://i.cs.hku.hk/~cwu/papers/gmsheng-NL2Code24.pdf
Alibaba Qwen teamhttps://github.com/QwenLM/
All Hands AIhttps://www.all-hands.dev/
ModelBesthttp://modelbest.cn/
StepFunhttps://www.stepfun.com/
Camel-AIhttps://www.camel-ai.org/
OpenManushttps://github.com/OpenManus
Baichuanhttps://www.baichuan-ai.com/home
RedNotehttps://www.xiaohongshu.com/
SwissAIhttps://www.swiss-ai.org/
Moonshot AI (Kimi)https://www.moonshot-ai.com/
IceSword Labhttps://www.iceswordlab.com
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#awesome-work-using-verl
TinyZerohttps://github.com/Jiayi-Pan/TinyZero
https://camo.githubusercontent.com/3fd6e7fde27a8e6c01cc1e5c7a46e4da301ff82457483eaf0cd45e0372346ba6/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4a696179692d50616e2f54696e795a65726f
SkyThoughthttps://github.com/NovaSky-AI/SkyThought
https://camo.githubusercontent.com/0e3de8760ee4e55828cc85b7c7b1dfa63e61c8496d1b50bfffbc79f6ea52acfe/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4e6f7661536b792d41492f536b7954686f75676874
simpleRL-reasonhttps://github.com/hkust-nlp/simpleRL-reason
https://camo.githubusercontent.com/4df97c2a2aa6f6cca1ebb402a18e2c241f5f1b4a8f899d809ad734e106bc177e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f686b7573742d6e6c702f73696d706c65524c2d726561736f6e
Easy-R1https://github.com/hiyouga/EasyR1
https://camo.githubusercontent.com/80b172788a823a2b4d053025801367b3e76d61074e7133833a26c280c6cd6bd0/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6869796f7567612f456173795231
OpenManus-RLhttps://github.com/OpenManus/OpenManus-RL
https://camo.githubusercontent.com/5b3c797f8af70d23ad6a95f82743b7f4170da65a6e4db32ba510f9c3fb91993a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f70656e4d616e75732f4f70656e4d616e75732d524c
rllmhttps://github.com/agentica-project/rllm
verl-pipelinehttps://github.com/agentica-project/verl-pipeline
https://camo.githubusercontent.com/62a1f59de57fe194a62b1f7a4d8bc486058125b8cb00614bb49334a5bb33785d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6167656e746963612d70726f6a6563742f726c6c6d
RAGENhttps://github.com/ZihanWang314/ragen
https://camo.githubusercontent.com/d964a9af75af82066b38510180f82985df858f86853ac5bc421be5f635fd036b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5a6968616e57616e673331342f726167656e
Search-R1https://github.com/PeterGriffinJin/Search-R1
https://camo.githubusercontent.com/e858d3c278cdf2dca4fff81dd8d647da15bbc369525c6c10b8d3d7f8b5e72867/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f50657465724772696666696e4a696e2f5365617263682d5231
ReSearchhttps://github.com/Agent-RL/ReSearch
https://camo.githubusercontent.com/1eee2fb0ea5cbabed40c8420d8c0cd08802a524a5b753538bb91ae2d0ec7b710/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4167656e742d524c2f5265536561726368
Skywork-OR1https://github.com/SkyworkAI/Skywork-OR1
https://camo.githubusercontent.com/8bffe5d8af3859233c973628597750c84b78177a9668d38cddfee2776e6d3526/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f536b79776f726b41492f536b79776f726b2d4f5231
ToRLhttps://github.com/GAIR-NLP/ToRL
https://camo.githubusercontent.com/1814ae888a444f6f48d4cd46e04ca26005e642b892660d7df4026fb56a0a751e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f474149522d4e4c502f546f524c
Absolute Zero Reasonerhttps://github.com/LeapLabTHU/Absolute-Zero-Reasoner
A no human curated data self-play framework for reasoninghttps://arxiv.org/abs/2505.03335
https://camo.githubusercontent.com/36ba3861a09780d5e34982c75f994c2bd00eb79442a289587516a91db98ffd6f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4c6561704c61625448552f4162736f6c7574652d5a65726f2d526561736f6e6572
verl-agenthttps://github.com/langfengQ/verl-agent
https://camo.githubusercontent.com/78146232456d31cf2794a48595787394f3004e7f4fcb32dc4863ad4484acf3b2/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c616e6766656e67512f7665726c2d6167656e74
RL-Factoryhttps://github.com/Simple-Efficient/RL-Factory
https://camo.githubusercontent.com/6651891ae91949a4b5a339acdba43653a1db057ef31340f32149ea806e82896b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f53696d706c652d456666696369656e742f524c2d466163746f7279
ReToolhttps://retool-rl.github.io/
verl-toolhttps://github.com/TIGER-AI-Lab/verl-tool
https://camo.githubusercontent.com/f0b080c8286c896b60e5bbb97d023f516e58b33890937a4da986f0f59d60f31b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f54494745522d41492d4c61622f7665726c2d746f6f6c
PRIMEhttps://github.com/PRIME-RL/PRIME
https://camo.githubusercontent.com/480458684595bfe8708f52142ef323c06e4a975f0cc4e9ed1237918dc33e7d0f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5052494d452d524c2f5052494d45
MemAgenthttps://github.com/BytedTsinghua-SIA/MemAgent
https://camo.githubusercontent.com/47e8d4c141c2cd1630d30e757612e404516cb9e595458b8cf1bf223296a2bb11/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f42797465645473696e676875612d5349412f4d656d4167656e74
POLARIShttps://github.com/ChenxinAn-fdu/POLARIS
https://camo.githubusercontent.com/0653020ccac0748b46e0030d1b5138e54ed61a99318710eb936a77cbdc9a3a14/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4368656e78696e416e2d6664752f504f4c41524953
GUI-R1https://github.com/ritzz-ai/GUI-R1
https://camo.githubusercontent.com/0c4448737a5d7facc0bc424942512143b993f6fe6fd90dbe0e184e1d5e6eda3e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7269747a7a2d61692f4755492d5231
DeepRetrievalhttps://github.com/pat-jj/DeepRetrieval
https://camo.githubusercontent.com/4aa4c1a8e4b666a370ff1152caad060f6c3cd07c0486a6d9908ddf86768a1ede/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7061742d6a6a2f4465657052657472696576616c
Code-R1https://github.com/ganler/code-r1
https://camo.githubusercontent.com/5078de0a738d14c80edf40bd2394d8fab49460b557a45eafc873c5bf5f406e0e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f67616e6c65722f636f64652d7231
DeepResearcherhttps://github.com/GAIR-NLP/DeepResearcher
https://camo.githubusercontent.com/2668ffa20a8978dd056f0b3fa19210cb5fbee46d51e2dcad4157f0edc7b86039/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f474149522d4e4c502f4465657052657365617263686572
VAGENhttps://github.com/RAGEN-AI/VAGEN
https://camo.githubusercontent.com/1928d30bab587862070665ac60f2aca3e32e60e88faaf01727d376da2ddb3d49/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f524147454e2d41492f564147454e
RM-R1https://arxiv.org/abs/2505.02387
https://camo.githubusercontent.com/437dfac8f0d0aa4cff7459a9366b84ddf309225e8455278f82f98dc9ec42cd32/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f524d2d52312d554955432f524d2d5231
LUFFYhttps://arxiv.org/pdf/2504.14945
https://camo.githubusercontent.com/eef260b95a46690b570c6f417874f3cf46f1d7ed5771568e562efcfdce9d7bf9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f456c6c696f747459616e2f4c55464659
DeepMathhttps://github.com/zwhe99/DeepMath
https://camo.githubusercontent.com/470b98415a94e3557e3aa04aea2da5e1216f7c71baec2d7447071ac84812a70f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7a77686539392f446565704d617468
Entropy Mechanism of RLhttps://github.com/PRIME-RL/Entropy-Mechanism-of-RL
https://camo.githubusercontent.com/7c3c336a1d54925da31118e665a9ea174cf6b6fa3b9af2c389da81faaefc0217/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5052494d452d524c2f456e74726f70792d4d656368616e69736d2d6f662d524c
LLaSA-TTS-GRPOhttps://github.com/channel-io/ch-tts-llasa-rl-grpo
https://camo.githubusercontent.com/384cbbbd5d959af27fec6d51a7d8bf3020e3387d64b7e9e81a40d174334e6142/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6368616e6e656c2d696f2f63682d7474732d6c6c6173612d726c2d6772706f
PF-PPOhttps://arxiv.org/abs/2409.06957
RACROhttps://github.com/gyhdog99/RACRO2
https://camo.githubusercontent.com/923598b7863204a65774a587af0b6fd93e9311a289d133e5d505487bd8ca9db6/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f677968646f6739392f524143524f32
recipehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/recipe/README.md
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#contribution-guide
contributions guidehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/blob/main/CONTRIBUTING.md
ByteDance Seed Teamhttps://team.doubao.com/
https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#about-bytedance-seed-team
https://team.doubao.com/
https://github.com/user-attachments/assets/469535a8-42f2-4797-acdf-4f7a1d4a0c3e
https://www.xiaohongshu.com/user/profile/668e7e15000000000303157d?xsec_token=ABl2-aqekpytY6A8TuxjrwnZskU-6BsMRE_ufQQaSAvjc%3D&xsec_source=pc_search
https://www.zhihu.com/org/dou-bao-da-mo-xing-tuan-dui/
Readme https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#readme-ov-file
Apache-2.0 license https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#Apache-2.0-1-ov-file
Contributing https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork#contributing-ov-file
Please reload this pagehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
Activityhttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/activity
Custom propertieshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/custom-properties
0 starshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/stargazers
0 watchinghttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/watchers
0 forkshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/forks
Report repository https://patch-diff.githubusercontent.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2FNovaSky-AI%2Fverl-fork&report=NovaSky-AI+%28user%29
Releaseshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/releases
Packages 0https://patch-diff.githubusercontent.com/orgs/NovaSky-AI/packages?repo_name=verl-fork
Contributors 291https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/graphs/contributors
Please reload this pagehttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork
+ 277 contributorshttps://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/graphs/contributors
Python 93.8% https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/search?l=python
Shell 5.7% https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/search?l=shell
Roff 0.5% https://patch-diff.githubusercontent.com/NovaSky-AI/verl-fork/search?l=roff
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.