Skip to content

Pull requests: redai-infra/Relax

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

feat(dr-grpo): add Dr.GRPO support
#239 opened Aug 4, 2026 by idvzchusvol Loading…
5 of 11 tasks
No.41 SDPO实现与复现
#237 opened Aug 4, 2026 by ZiyiTsang Draft
5 of 7 tasks
feat(p3o): add ESS-adaptive policy optimization
#234 opened Aug 4, 2026 by DreamEnding Contributor Draft
3 of 11 tasks
perf(megatron): reuse process groups for colocate weight sync
#229 opened Aug 3, 2026 by ldemon2333 Loading…
3 of 12 tasks
feat(klx):add qwen35-9B-vl script
#227 opened Aug 3, 2026 by yeqinghe609 Contributor Loading…
11 tasks
【NO.28】实现 RLOO advantage estimator
#205 opened Aug 1, 2026 by xcosmosbox Loading…
11 of 16 tasks
[No.35] feat(doctor): add config doctor and dry-run
#204 opened Aug 1, 2026 by AutumnCs Loading…
8 of 14 tasks
Task.17】DeepEyes processor 动态 patch
#188 opened Jul 30, 2026 by yuki-younai Loading…
[Task 24] Make Qwen3-VL SGLang router policy configurable
#185 opened Jul 30, 2026 by huxy1225-cloud Contributor Draft
8 of 10 tasks
feat(rloo): add synchronous training baseline
#182 opened Jul 30, 2026 by Dayuxiaoshui Contributor Loading…
2 of 11 tasks
No.30: feat(dr-grpo), Add Dr.GRPO Support
#173 opened Jul 29, 2026 by ZiyiTsang Loading…
5 of 6 tasks
【No.35】 feat(doctor): add config doctor dry-run
#168 opened Jul 29, 2026 by howtomakeaname Loading…
4 tasks done
【NO.20】优化多轮 Rollout 请求调度
#161 opened Jul 28, 2026 by WXLL330 Draft
4 of 5 tasks
ProTip! Updated in the last three days: updated:>2026-08-01.