verl: Volcano Engine Reinforcement Learning for LLMs
active 2025-09-22 → 2026-03-04 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 164 days from 2025-09-22 to 2026-03-04. Pushes: 176 total, peak 15 in a day. Pull requests: 33 total, peak 8 in a day. Issues: 0 total, peak 0 in a day. Comments: 45 total, peak 11 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| 0oshowero0 | 109 | 92 | 11 | 1 |
| Copilot | 51 | 0 | 0 | 37 |
| ji-huazhong | 36 | 28 | 5 | 1 |
| MissFishY | 26 | 26 | 0 | 0 |
| baymax591 | 14 | 13 | 1 | 0 |
| LLLLxmmm | 12 | 2 | 8 | 2 |
| dodatboii | 11 | 11 | 0 | 0 |
| jianjunzhong | 8 | 2 | 6 | 0 |
| coderabbitai[bot] | 4 | 0 | 0 | 4 |
| zhabuye | 2 | 0 | 2 | 0 |
| Chase-Rong | 2 | 2 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#51jianjunzhong2026-01-13 09:43
- Pull request#50jianjunzhong2025-12-20 09:03
- Issue comment#49coderabbitai[bot]2025-11-25 03:16[BREAKING][worker, rollout, vllm] feat: implement vLLM co-located training-inference rollout with process separation
- Pull request#49jianjunzhong2025-11-25 03:16
- Pull request#49jianjunzhong2025-11-25 03:16
- Pull request#48ji-huazhong2025-11-18 04:38
- Pull request#46LLLLxmmm2025-11-17 06:35
- Issue comment#46coderabbitai[bot]2025-11-17 06:33[recipe] fix: Remove useless code
- Pull request#46LLLLxmmm2025-11-17 06:33
- Issue comment#44coderabbitai[bot]2025-11-17 02:39[recipe, TransderQueue] fix: remove unused param get_n_samples & update _balance_batch func
- Pull request#44LLLLxmmm2025-11-17 02:38
- Issue comment#43coderabbitai[bot]2025-11-07 08:18[data] feat: TransferQueue - Support managing multiple data partitions for Train/Val/Test in controller
- Issue comment#41LLLLxmmm2025-10-17 09:01inherit RayPPOTrainer & adapt for multimodal data format
- Pull request#40baymax5912025-10-16 12:05
- Pull request#37LLLLxmmm2025-10-15 07:11
- Pull request#36ji-huazhong2025-10-15 06:45
- Pull request#240oshowero02025-09-30 08:48
- Pull request#19jianjunzhong2025-09-29 12:30
- Pull request#210oshowero02025-09-29 08:23
- Pull request#20ji-huazhong2025-09-29 07:05
- Pull request#18ji-huazhong2025-09-29 02:52
- Pull request#17ji-huazhong2025-09-29 02:23
- Pull request#150oshowero02025-09-29 01:15
- Pull request#150oshowero02025-09-29 01:15
- Pull request#140oshowero02025-09-29 01:07
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.