-
Notifications
You must be signed in to change notification settings - Fork 3.6k
Pull requests: verl-project/verl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: flatten multi-component position_ids to 1D for nested tensor compatibility
#5886
opened Apr 6, 2026 by
yifannnwu
Loading…
1 of 2 tasks
fix: sync strategy from ActorConfig/CriticConfig to EngineConfig
#5885
opened Apr 6, 2026 by
yifannnwu
Loading…
3 tasks done
[megatron] fix: enable_routing_replay fails with MLATransformerConfig…
#5884
opened Apr 6, 2026 by
NoonePauseferg
Loading…
3 of 7 tasks
[model] fix: replace inplace += with out-of-place addition in dummy visual forward
#5881
opened Apr 4, 2026 by
reonokiy
Loading…
7 tasks done
[megatron] fix: dynamic context parallel batch splitting and loss normalization
#5869
opened Apr 2, 2026 by
Kite0011
Loading…
8 tasks
[sglang] Adapting the use of _launch_subprocesses to the latest SGLang branch
#5868
opened Apr 2, 2026 by
xiazhahe
Loading…
8 tasks
feature: Enhance Ray subprocess error handling system
#5855
opened Apr 2, 2026 by
abeiabeiqq
Loading…
[megatron] feat: enable Megatron FSDP for SFT training
#5854
opened Apr 1, 2026 by
yxs
Loading…
4 tasks done
[megatron] fix: always patch actor postprocess on unfused path for MTP models
#5845
opened Apr 1, 2026 by
AkiRusProd
Loading…
[doc] feat: add Claude Code skills for add-dataset, add-reward, add-trainer
#5844
opened Apr 1, 2026 by
khazic
Loading…
3 tasks done
[doc, misc] chore: add Claude Code skills and CLAUDE.md for AI-assisted development
#5843
opened Apr 1, 2026 by
khazic
Loading…
4 tasks done
[trainer] feat: add group reward std and gradient SNR metrics to compute_data_metrics
#5842
opened Apr 1, 2026 by
KLGR123
Loading…
3 tasks done
[rollout] chore: bump up trtllm version to 1.3.0rc10
#5841
opened Apr 1, 2026 by
Superjomn
Loading…
6 of 8 tasks
[reward] fix: restore timeout in math_verify via ProcessPoolExecutor
#5839
opened Apr 1, 2026 by
MaxwellJryao
Loading…
4 of 6 tasks
[perf, fsdp, trainer] feat: Skip training for zero-advantage responses to speed up RL.
#5838
opened Apr 1, 2026 by
sheilaliuxl
Loading…
7 tasks done
[examples] Add NPU-adapted GSM8K on-policy distillation launcher
#5837
opened Apr 1, 2026 by
duesdues
Loading…
[doc,model] feat: Add Qwen3-235B NPU Long Sequence Optimizing Practice
#5835
opened Apr 1, 2026 by
Vvictorrrr
Loading…
5 of 8 tasks
[trainer,rollout,algo] feat: (MOPD, 1/3) Multi-Teacher Model and Server Managers
#5834
opened Apr 1, 2026 by
JacobHelwig
Loading…
[training_utils] fix: mrope position_ids preprocess bug fix
#5829
opened Mar 31, 2026 by
ZLiao097
Loading…
4 of 8 tasks
feat(rollout-skip): add dump_steps list parameter to specify particular dump steps
#5812
opened Mar 30, 2026 by
zyang6
Loading…
6 tasks
[trainer] fix: serialize numpy rollout metadata in rollout_data_dir dumps
#5810
opened Mar 30, 2026 by
chenshui223
Loading…
[ci, vllm] chore: update vllm-omni 0.18.0 official release and Miscellaneous
#5809
opened Mar 30, 2026 by
AndyZhou952
Loading…
8 tasks done
Previous Next
ProTip!
Updated in the last three days: updated:>2026-04-03.