-
Notifications
You must be signed in to change notification settings - Fork 521
Pull requests: areal-project/AReaL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(rollout): add min_valid_group_size to drop under-filled rollout groups
#1416
opened Jun 16, 2026 by
EazyReal
Loading…
fix(ppo): group-normalize by actual group sizes for partial groups
#1415
opened Jun 16, 2026 by
EazyReal
Loading…
fix(awex): allow disabling batch_send_recv use_group via AWEX_WU_USE_GROUP
#1414
opened Jun 16, 2026 by
sitabulaixizawaluduo
Collaborator
Loading…
5 of 15 tasks
fix(openai): render tool-call arguments as a mapping for HF chat templates
#1411
opened Jun 16, 2026 by
EazyReal
Loading…
feat(experimental): Diffusion RL post-training — Phase 1 PoC (SD1.5 + LoRA + REINFORCE)
#1410
opened Jun 15, 2026 by
daoluzixin
Loading…
5 of 6 tasks
fix: per-sample version tracking with loss_mask filter and multi-turn…
#1408
opened Jun 13, 2026 by
pyq623
Loading…
feat: trajectory dump/replay for offline training-loop debugging
#1407
opened Jun 12, 2026 by
daoluzixin
Loading…
5 of 9 tasks
Support Megatron FP8 weight transfer in AWEX colocate mode
#1406
opened Jun 11, 2026 by
equation314
Loading…
8 of 14 tasks
ci: add PyPI publish workflow and fix Megatron deps 🚀
#1404
opened Jun 10, 2026 by
mingcheng
Contributor
Loading…
7 of 15 tasks
feat(megatron): make MTP head opt-in to support Qwen3.6 MoE RL
#1403
opened Jun 9, 2026 by
Adiactive
Contributor
Loading…
7 of 15 tasks
feat(distillation): Multi-Teacher On-Policy Distillation Support
#1400
opened Jun 8, 2026 by
zahrayousefijamarani
Contributor
Loading…
6 of 15 tasks
fix: Prevent workers from applying dp-scaled staleness to fix rollout hanging issues caused by zero local capacity
#1396
opened Jun 8, 2026 by
zcsh
Loading…
3 of 14 tasks
feat: disable megatron grad buffers CPU backup to save host memory
#1393
opened Jun 7, 2026 by
HT-Yuan
Collaborator
Loading…
1 of 15 tasks
fix: add group_id to StartSessionRequest for online GRPO session grouping
#1392
opened Jun 5, 2026 by
Oxygen56
Loading…
feat(experimental): enable DTA training for Archon DP
#1391
opened Jun 5, 2026 by
ezoicoder
Collaborator
Loading…
8 of 15 tasks
feat(agent_service): add OpenClaw per-session agent runtime
#1383
opened Jun 2, 2026 by
IF007
Loading…
4 tasks done
feat(mcore): add GLM-5/DeepSeek-V3 model support (mbridge + megatron-bridge)
#1373
opened May 28, 2026 by
dingzhiqiang
Collaborator
Loading…
4 tasks
feat(mcore): add Bailing-MoE V2.5 megatron-bridge adapter
#1372
opened May 28, 2026 by
dingzhiqiang
Collaborator
Loading…
3 tasks
fix(fsdp engine): localize DTensor norm output for Qwen models in TP
#1365
opened May 25, 2026 by
HT-Yuan
Collaborator
Loading…
1 of 15 tasks
feat[v2]: Support PD Disaggregation: DP=2(1P1D),TP=n
#1364
opened May 25, 2026 by
ZiyiTsang
Collaborator
Loading…
2 of 7 tasks
feat(awex): FSDP colocate weight update via CUDA IPC
#1361
opened May 22, 2026 by
guozhihao-224
Collaborator
Loading…
6 of 17 tasks
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.