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 }}
AL-377
/
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 18, 2026
add: riddle preprocess
testljt
committed
8ac4ac7
View commit details
Copy full SHA for 8ac4ac7
Browse repository at this point
Commits on Feb 17, 2026
add: eval entry points
testljt
committed
9019b21
View commit details
Copy full SHA for 9019b21
Browse repository at this point
add: support math and gpqa
testljt
committed
73a8c9e
View commit details
Copy full SHA for 73a8c9e
Browse repository at this point
add: support math and gpqa
testljt
committed
eac7331
View commit details
Copy full SHA for eac7331
Browse repository at this point
add: support math and gpqa
testljt
committed
1f561c8
View commit details
Copy full SHA for 1f561c8
Browse repository at this point
update: recipe
testljt
committed
93e056b
View commit details
Copy full SHA for 93e056b
Browse repository at this point
udpate: recipe
testljt
committed
1ee0bda
View commit details
Copy full SHA for 1ee0bda
Browse repository at this point
Commits on Feb 16, 2026
fix: key for save hf
testljt
committed
3b7ea64
View commit details
Copy full SHA for 3b7ea64
Browse repository at this point
update: exp name
testljt
committed
4bd30c2
View commit details
Copy full SHA for 4bd30c2
Browse repository at this point
fix: remove tool template auto involve
testljt
committed
1ce8887
View commit details
Copy full SHA for 1ce8887
Browse repository at this point
update: save logs
testljt
committed
6ca460e
View commit details
Copy full SHA for 6ca460e
Browse repository at this point
update
testljt
committed
484db8c
View commit details
Copy full SHA for 484db8c
Browse repository at this point
add: riddle new sp && verify by judge
testljt
committed
187d9db
View commit details
Copy full SHA for 187d9db
Browse repository at this point
add:test
testljt
committed
4a5fa79
View commit details
Copy full SHA for 4a5fa79
Browse repository at this point
add: riddle data preprocess and verify
testljt
committed
d38d2fb
View commit details
Copy full SHA for d38d2fb
Browse repository at this point
[docs] Add new awesome work using Verl (#5328)
Show description for e8a484c
MING-ZCH
authored
e8a484c
View commit details
Copy full SHA for e8a484c
Browse repository at this point
Commits on Feb 14, 2026
[fsdp,algo] feat: add NVFP4 QAT (Quantization-Aware Training) support (#5190)
Show description for 27f65f1
zhangyimi
authored
27f65f1
View commit details
Copy full SHA for 27f65f1
Browse repository at this point
[veomni, trainer] fix: padding pixel value with padding_scale for vl model (#5322)
Show description for 8c41724
3 people
authored
8c41724
View commit details
Copy full SHA for 8c41724
Browse repository at this point
[rollout] fix: make skip rollout compatible with async mode (#5320)
Show description for cf97337
ChengQianqian
authored
cf97337
View commit details
Copy full SHA for cf97337
Browse repository at this point
[misc] refactor: delete remaining batch-mode code in single controller (#5319)
Show description for 395938b
ji-huazhong
authored
395938b
View commit details
Copy full SHA for 395938b
Browse repository at this point
[ci] fix: main pre-commit (#5318)
Show description for 0c5cc48
pengwu22
authored
0c5cc48
View commit details
Copy full SHA for 0c5cc48
Browse repository at this point
Commits on Feb 13, 2026
[megatron] feat: Support LoRA training with FP16 using Megatron-Bridge. (#4648)
Show description for ec123e6
xichengpro
authored
ec123e6
View commit details
Copy full SHA for ec123e6
Browse repository at this point
[model,cfg] fix: type annotation for Lora target_modules (#5223)
Show description for 536a978
thvasilo
and
gemini-code-assist[bot]
authored
536a978
View commit details
Copy full SHA for 536a978
Browse repository at this point
[fsdp, vllm] feat: add NPU GRPO training scripts for Qwen3-VL-30B (FSDP/VLLM backends) (#5260)
Show description for 2703d73
alwaysyiyu
authored
2703d73
View commit details
Copy full SHA for 2703d73
Browse repository at this point
[fsdp, vllm] feat: add NPU GRPO training scripts for Qwen3-VL-8B (FSDP/VLLM backends) (#5250)
Show description for a22d51e
zhihaofang1017
authored
a22d51e
View commit details
Copy full SHA for a22d51e
Browse repository at this point
[algo] feat: add NPU SAPO training script for Qwen3-8B (FSDP/vLLM backends) (#5257)
Show description for 9917f76
3 people
authored
9917f76
View commit details
Copy full SHA for 9917f76
Browse repository at this point
[worker, tool] fix: stabilize agent loop extra fields schema (#5301)
Show description for 9682330
3 people
authored
9682330
View commit details
Copy full SHA for 9682330
Browse repository at this point
[trtllm] feat: use max utilization scheduler by default (#5302)
Show description for 4dd4980
tongyuantongyu
authored
4dd4980
View commit details
Copy full SHA for 4dd4980
Browse repository at this point
[veomni] refactor: Modify dp related parameters to align with FSDP backend and remove temporarily unsupported TP/PP/CP parameters (#5303)
Show description for a43eecb
ChengQianqian
and
ji-huazhong
authored
a43eecb
View commit details
Copy full SHA for a43eecb
Browse repository at this point
Commits on Feb 12, 2026
[fsdp,veomni] fix: remove FSDPUlyssesShardingManager to make eval_mode/train_mode reentrant (#5305)
Show description for 9cb89d8
wuxibin89
authored
9cb89d8
View commit details
Copy full SHA for 9cb89d8
Browse repository at this point
[doc] chore: gspo update config and add version with npu (#5279)
Show description for 8bcf908
chengminhua
authored
8bcf908
View commit details
Copy full SHA for 8bcf908
Browse repository at this point
[reward] fix: reward model args and reward_kwargs bug (#5289)
Show description for 92c454a
yyDing1
authored
92c454a
View commit details
Copy full SHA for 92c454a
Browse repository at this point
Commits on Feb 11, 2026
[reward] fix: backward compatibility with old reward config (#5287)
Show description for 018f8dc
yyDing1
authored
018f8dc
View commit details
Copy full SHA for 018f8dc
Browse repository at this point
[megatron] fix: fallback to moe_router_padding_for_fp8 in router replay patch (#5283)
Show description for a4ae296
xhx1022
authored
a4ae296
View commit details
Copy full SHA for a4ae296
Browse repository at this point
[misc] chore: fix veomni_trainer.yaml (#5285)
Show description for 12b6382
wuxibin89
authored
12b6382
View commit details
Copy full SHA for 12b6382
Browse repository at this point
Previous
Next
You can’t perform that action at this time.