Skip to content

Pull requests: NovaSky-AI/SkyRL

New pull request New
169 Open 1,289 Closed
169 Open 1,289 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

[SFT] Stateful dataloader and custom samplers for SFTTrainer
#1842 opened Jun 26, 2026 by avigyabb • Draft
[megatron] fused linear cross-entropy for 23x memory savings at 262k context
#1841 opened Jun 26, 2026 by casper-hansen Loading…
@erictang000
10
[codex] Add Tinker checkpoint delete endpoint
#1840 opened Jun 26, 2026 by j316chuck • Draft
1
[megatron] add opt-in async distributed checkpoint save
#1838 opened Jun 26, 2026 by dinhxuanvu Contributor Loading…
3 tasks
3
feat: Arctic RL training backend integration
#1837 opened Jun 26, 2026 by sfc-gh-kganesan Loading…
3 of 4 tasks
6
[generator] Add per global_step cache salt for each trajectory to invalidate super stale KV
#1836 opened Jun 26, 2026 by erictang000 Collaborator Loading…
7
[refactor] Remove legacy inference codepath
#1835 opened Jun 26, 2026 by SumanthRH Member • Draft
[feat] Add Spec Decoding and MTP training support
#1832 opened Jun 25, 2026 by zanderjiang Contributor Loading…
6
[megatron] add opt-in distributed HF checkpoint export
#1831 opened Jun 25, 2026 by dinhxuanvu Contributor Loading…
3
Make packed sequence alignment FP8-safe
#1828 opened Jun 24, 2026 by jinghanyao1-hub Collaborator Loading…
@erictang000
13
[fix] Memory-map dataset per SFT tokenize worker to avoid cache stampede
#1826 opened Jun 23, 2026 by dinhxuanvu Contributor Loading…
3
UI/UX: Poor Error Handling UX in Async Dispatcher
#1823 opened Jun 22, 2026 by tomaioo Loading…
2
fix(generators): compute batched rollout metrics from truncated responses
#1821 opened Jun 21, 2026 by EazyReal Loading…
fix(tracking): finalize MLflow runs on SIGTERM instead of leaving them RUNNING
#1819 opened Jun 20, 2026 by EazyReal Loading…
1
6
[megatron] Enable Nemotron-3-Ultra-550B GRPO RL + fix multi-rank (EP>16/PP>2) weight sync
#1816 opened Jun 19, 2026 by erictang000 Collaborator Loading…
5
[algorithm] add rollout KL loss + fix padding-microbatch field drops
#1811 opened Jun 19, 2026 by erictang000 Collaborator Loading…
3
[train] Async batch collation (double-buffering) for the SFT trainer
#1809 opened Jun 18, 2026 by dyurk-lila Loading…
2 tasks done
2
[train] Vectorize controller-side training-batch collation (SFT + RL)
#1808 opened Jun 18, 2026 by dyurk-lila Loading…
3 tasks done
7
[train] Skip building unused per-token loss_fn_outputs when the caller does not consume them
#1807 opened Jun 18, 2026 by dyurk-lila Loading…
[megatron] Stream ChunkedDistributedLogprob.backward into a preallocated buffer (lower peak memory)
#1806 opened Jun 18, 2026 by dyurk-lila Loading…
@erictang000
2
[megatron] Accept dtype-string optimizer_config_kwargs (coerce exp_avg_dtype etc. to torch.dtype)
#1805 opened Jun 18, 2026 by dyurk-lila Loading…
@erictang000
2
rename adv_estimator param to advantage_estimator in compute_advantages_and_returns
#1793 opened Jun 16, 2026 by KTanmay1 Loading…
1 task
1
[train] Save HF processor on checkpoint export for VLMs
#1785 opened Jun 14, 2026 by dinhxuanvu Contributor Loading…
1 of 2 tasks
10
[fix] Honor served_model_name and surface HTTP errors in RemoteInferenceEngine
#1783 opened Jun 13, 2026 by discobot Contributor Loading…
1
3
[fix] Use masked mean in advantage batch normalization
#1782 opened Jun 12, 2026 by discobot Contributor Loading…
1
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.