Skip to content

Pull requests: NovaSky-AI/SkyRL

New pull request New
67 Open 689 Closed
67 Open 689 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

[WIP] Stack weights
#996 opened Jan 30, 2026 by raulchen Loading…
5 tasks done
2
[tx] Add GLM4.7
#989 opened Jan 29, 2026 by tanmaysachan Loading…
3 tasks done
8
[train][harbor] Suppress excessive harbor/litellm loggings
#987 opened Jan 29, 2026 by CharlieFRuan Loading…
2
Add Tinker API server for supervised fine-tuning with SkyRL backend
#986 opened Jan 29, 2026 by tyler-griggs • Draft
4 tasks
[tx] Support LoRA in the unembedding layer, redux tx
#984 opened Jan 28, 2026 by pcmoritz Loading…
6
fix: rope_scaling for vLLM and HuggingFace context extension
#976 opened Jan 27, 2026 by dzorlu Loading…
1 task
[tx] Add max_micro_batches to limit batch size for forward/forward_backward requests tx
#968 opened Jan 26, 2026 by raulchen Loading…
4
[WIP] [tx] Make it easy to run on a multi-node Ray cluster tx
#955 opened Jan 25, 2026 by Future-Outlier Loading…
6
Separate infrastructure logs from training progress
#953 opened Jan 25, 2026 by tyler-griggs Loading…
2 of 3 tasks
4
Add SKYRL_LOG_LEVEL env var and suppress verbose Ray logs by default
#947 opened Jan 25, 2026 by tyler-griggs Loading…
1 of 2 tasks
2
Add Pydantic Configuration System with CLI Override Support
#946 opened Jan 25, 2026 by tyler-griggs Loading…
11
Stage 5: Add TinkerTrainingAdapter for forward_backward/optim_step
#938 opened Jan 24, 2026 by tyler-griggs Loading…
7
[skyrl-train][inference] HTTP Inference Integration (Feature-Flagged) 4/N
#931 opened Jan 24, 2026 by kouroshHakha • Draft
[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
DSPy integration
#921 opened Jan 22, 2026 by Harryllh Loading…
[tx] add per-layer gradient checkpointing with scan for memory-efficient training tx
#906 opened Jan 21, 2026 by raulchen Loading…
4 tasks done
10
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
[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
[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
skyrl-agent osworld integration
#875 opened Jan 14, 2026 by shuo-yuan Loading…
@caoshiyi @SumanthRH
2
ProTip! Filter pull requests by the default branch with base:main.