Skip to content

Pull requests: volcengine/verl

New pull request New
297 Open 2,386 Closed
297 Open 2,386 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[worker, training_utils] fix: Engine Metric Aggregation (Simple)
#4785 opened Jan 4, 2026 by JacobHelwig Loading…
2
[sglang] feat: Support SGLang remote_instance
#4784 opened Jan 4, 2026 by EduardDurech Loading…
2
[fix][rollout] fix accuracy issue in verl + vllm-ascend + dp+ep+tp+server scenarios
#4783 opened Jan 4, 2026 by leo-pony • Draft
4 of 7 tasks
3
[recipe] fix: workaround for making the one-step off-policy recipe compatible with IPv6 environments on Ascend NPU
#4782 opened Jan 4, 2026 by ji-huazhong Loading…
7 tasks
4
bugfix vllm-rollout update weights
#4780 opened Jan 4, 2026 by Annarine Loading…
7 tasks
2
[worker, training_utils] fix: Engine Metric Aggregation
#4778 opened Jan 4, 2026 by JacobHelwig Loading…
16
[ckpt] feat: add checkpoint-engine abstraction
#4775 opened Jan 3, 2026 by wuxibin89 Loading…
5
[checkpoint] fix: normalize LoRA state_dict keys when saving HF model
#4770 opened Jan 2, 2026 by yurekami Loading…
4 of 5 tasks
1
6
[trainer,data,algo] feat: Unify SFT and PPO Pipelines
#4766 opened Jan 2, 2026 by JacobHelwig Loading…
5
[perf]feat: Add MFU for Qwen3-VL dense
#4753 opened Dec 31, 2025 by zhihaofang1017 Loading…
7 tasks
4
[WIP][tool] feature: scheduling analysis based on profiling data
#4746 opened Dec 31, 2025 by tardis-key • Draft
7 tasks
4
[rollout] fix: remove redundant system message added in ToolAgentLoop._handle_processing_tools_state
#4744 opened Dec 30, 2025 by m-Just Loading…
6 of 7 tasks
3
fix(fully_async): use rollout.total_epochs for total_rollout_steps calculation
#4736 opened Dec 30, 2025 by FarrenZhang Loading…
2 tasks done
[hardware] feat: support qwen3vl ON ASCEND NPU
#4734 opened Dec 30, 2025 by Seren-hao Loading…
7 tasks
8
fix(rollout): correct infer_tp calculation for multi-server weight sync
#4728 opened Dec 29, 2025 by yurekami Loading…
2 tasks
1
fix: add support for video data in Agent Loop and Qwen3 VL
#4727 opened Dec 29, 2025 by kaln27 Loading…
5 tasks done
6
fix(fsdp): handle param offloading in get_actor_weights_info
#4726 opened Dec 29, 2025 by yurekami Loading…
2 of 3 tasks
1
4
fix(registry): make reward manager registration idempotent
#4725 opened Dec 29, 2025 by yurekami Loading…
2 tasks done
1
3
examples: Add memory optimization examples and documentation
#4722 opened Dec 29, 2025 by yurekami Loading…
2 of 3 tasks
3
tests: Add gradient accumulation tests for all loss aggregation modes
#4721 opened Dec 29, 2025 by yurekami Loading…
1 of 2 tasks
1
3
docs: Add comprehensive OOM resolution guide
#4720 opened Dec 29, 2025 by yurekami Loading…
3 tasks
1
7
[recipe, fsdp] feat: support GPT-OSS-20B DAPO training script on ASCEND NPU
#4716 opened Dec 29, 2025 by mikequan0425 • Draft
2 of 7 tasks
3
[sglang] fix sglang TP+DP support / port bug
#4715 opened Dec 29, 2025 by hustmf Loading…
7 tasks
7
[perf] fix: correct torch profiler logic for distributed trace collection
#4707 opened Dec 28, 2025 by AkiRusProd Loading…
4
fix: use model_dump() for proper Pydantic serialization in token2text
#4706 opened Dec 28, 2025 by yurekami Loading…
3 tasks done
1
2
ProTip! Exclude everything labeled bug with -label:bug.