Skip to content

Pull requests: NovaSky-AI/SkyRL

New pull request New
133 Open 1,132 Closed
133 Open 1,132 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

[models] add nemotron 30b nano run scripts
#1612 opened May 2, 2026 by erictang000 Collaborator Loading…
3
[train] SFT 2/N: Support training on all assistant messages, add HF export support and num_epochs
#1611 opened May 2, 2026 by SumanthRH Member Loading…
@CharlieFRuan
4
[train] Default to chunked logprobs for Megatron
#1610 opened May 1, 2026 by SumanthRH Member • Draft
[train] Support streaming mini-batch (non-blocking async training)
#1607 opened May 1, 2026 by rishithayenumula Loading…
1
4
[models] Add nemotron-nano-30b-a3b to CI
#1603 opened Apr 30, 2026 by erictang000 Collaborator Loading…
2
[train] Use custom wheel for vllm-router for /chat/completions fix run_train_gpu_ci
#1601 opened Apr 30, 2026 by SumanthRH Member Loading…
5
Add FP8 text-to-SQL training script; drop SQLEnv stop-tag assertion
#1599 opened Apr 30, 2026 by hao-aaron Collaborator Loading…
10
[feat] Recursive language models (RLMs) environment
#1596 opened Apr 30, 2026 by sox8502 • Draft
1
Fix GPU assignment for Slurm-launched Ray clusters
#1592 opened Apr 29, 2026 by agolajko Contributor Loading…
1
4
Fix AssertionError during eval when val set size is not divisible by train_batch_size
#1589 opened Apr 29, 2026 by rishithayenumula Loading…
1
@CharlieFRuan
8
[feat] Multi-LoRA serving for RemoteInferenceClient
#1579 opened Apr 28, 2026 by hao-aaron Collaborator Loading…
3
[models] add gemma4 training script
#1576 opened Apr 27, 2026 by erictang000 Collaborator • Draft
Widen transformers for v5.6 and vllm==0.19.1
#1561 opened Apr 22, 2026 by jamesbraza Loading…
1
@erictang000
6
[train] Fix rollout metrics for step-wise and custom generators (sync / fully async)
#1556 opened Apr 22, 2026 by CharlieFRuan Member • Draft
1 of 3 tasks
6
[WIP] Add changes needed for FP8 megatron training
#1543 opened Apr 21, 2026 by pcmoritz Collaborator Loading…
9
[train][step-wise] Three correctness/efficiency fixes for step-wise training
#1539 opened Apr 20, 2026 by CharlieFRuan Member Loading…
4 tasks done
2
[skyrl] Preserve staged forward_backward loss_fn_outputs across DP ranks
#1534 opened Apr 19, 2026 by taivu1998 Loading…
1
9
Modify SkyRL Generator to Append Router Indices in Multi-Turn
#1530 opened Apr 17, 2026 by devpatelio Collaborator Loading…
5
Add FoldGRPO advantage estimator and process_rewards pipeline
#1514 opened Apr 15, 2026 by sumi-fleet-hub Loading…
@CharlieFRuan
6
SFT loss aggregation consistent with RL path
#1513 opened Apr 15, 2026 by agolajko Contributor Loading…
@SumanthRH @erictang000
11
fix(docker): optimize Dockerfile.megatron to reduce image size by 1.36 GB run_train_megatron_gpu_ci
#1499 opened Apr 11, 2026 by dinhxuanvu Loading…
11
Add ppo as alias for dual_clip policy loss type
#1481 opened Apr 8, 2026 by j316chuck • Draft
feat: add max_tokens_per_microbatch config for token-based micro-batching
#1477 opened Apr 8, 2026 by erictang000 Collaborator Loading…
5
feat: native Atropos-SHM integration and modular ingestion layer
#1473 opened Apr 7, 2026 by RUFFY-369 Loading…
10
[train] Enable expandable_segments to reduce GPU memory fragmentation run_train_gpu_ci
#1470 opened Apr 7, 2026 by CharlieFRuan Member • Draft
5 tasks done
1
7
ProTip! Exclude everything labeled bug with -label:bug.