Skip to content

Pull requests: NovaSky-AI/SkyRL

New pull request New
70 Open 632 Closed
70 Open 632 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

[tx] WIP
#933 opened Jan 24, 2026 by pcmoritz Loading…
2
[skyrl-train][inference] HTTP Inference Integration (Feature-Flagged) 4/N
#931 opened Jan 24, 2026 by kouroshHakha • Draft
[Tinker API Stage 3] Generator integration with use_tinker_sampling_api feature flag
#930 opened Jan 24, 2026 by tyler-griggs • Draft
3 tasks done
Add SkyRLInferenceClient adapter and Tinker API tests (Stage 2)
#929 opened Jan 23, 2026 by tyler-griggs • Draft
5 tasks done
Add Tinker-compatible sample() API to inference engine stack
#928 opened Jan 23, 2026 by tyler-griggs • Draft
1 of 2 tasks
[skyrl-train] Fix loss reduction by moving normalization to the advantage computation
#925 opened Jan 23, 2026 by justinvyu • Draft
1
Add loss_fn parameterization to forward_backward
#924 opened Jan 23, 2026 by tyler-griggs • Draft
3
[train][Harbor][1/N] Upstream Harbor integration
#923 opened Jan 22, 2026 by CharlieFRuan • Draft
DSPy integration
#921 opened Jan 22, 2026 by Harryllh Loading…
[skyrl-train][inference] Inference Client Hook Refactor (3/N)
#916 opened Jan 22, 2026 by kouroshHakha Loading…
6
[tx] add per-layer gradient checkpointing with scan for memory-efficient training tx
#906 opened Jan 21, 2026 by raulchen Loading…
4 tasks done
3
[skyrl-train][refactor] 2/N Inference Server Refactor -- RemoteInferenceClient
#904 opened Jan 20, 2026 by kouroshHakha Loading…
@CharlieFRuan
6
[tx] chunked logprobs computation for memory efficiency tx
#902 opened Jan 20, 2026 by raulchen Loading…
3 tasks done
1
Unify Megatron and FSDP training interfaces with forward_backward + optim_step
#901 opened Jan 20, 2026 by tyler-griggs Loading…
1 of 2 tasks
4
[train] Enable RayPrometheusStatLogger for async vLLM engine
#900 opened Jan 20, 2026 by kanwang Loading…
@CharlieFRuan
6
[skyrl-train][inference] Inference Server Refactor (1/N)
#899 opened Jan 20, 2026 by kouroshHakha Loading…
@CharlieFRuan
17
[skyrl-train] Add GDPO Support to PPO Utils
#897 opened Jan 19, 2026 by devpatelio Loading…
2 tasks
3
[tx] Implement cutlass kernel for ragged_dot with group_offset tx
#896 opened Jan 19, 2026 by pcmoritz Loading…
4
[tx] DeepseekV3 implementation tx
#889 opened Jan 16, 2026 by tanmaysachan Loading…
4 of 5 tasks
10
[skyrl-train] Update Megatron + LoRA to use PEFT only bridge
#885 opened Jan 15, 2026 by erictang000 • Draft
1 of 3 tasks
[algorithm] Sampling mask from Inference Engine Applies to Trainer
#883 opened Jan 15, 2026 by devpatelio Loading…
9
[skyrl-train] Add example for on-policy distillation with GOLD
#881 opened Jan 15, 2026 by pbokc • Draft
2
[tx] Cuda tile for expert parallelism tx
#880 opened Jan 15, 2026 by agolajko • Draft
4 tasks
[tx] Add cuDNN flash attention tx
#879 opened Jan 15, 2026 by raulchen Loading…
3 tasks
10
skyrl-agent osworld integration
#875 opened Jan 14, 2026 by shuo-yuan Loading…
2
ProTip! Updated in the last three days: updated:>2026-01-21.