Skip to content

Pull requests: NovaSky-AI/SkyRL

New pull request New
183 Open 1,346 Closed
183 Open 1,346 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

[feat][SFT] Ingest pretokenized datasets from local or object storage (S3/GCS)
#1927 opened Jul 18, 2026 by avigyabb Collaborator Loading…
3
[feat] Add suppport for mooncake connector for P/D; custom P/D init kwargs
#1926 opened Jul 17, 2026 by SumanthRH Member • Draft
[logging] Account for env setup and overhead in trajectory time
#1925 opened Jul 17, 2026 by eicherseiji Contributor • Draft
[logging] Log rollout buffer depth to W&B and Prometheus
#1924 opened Jul 17, 2026 by eicherseiji Contributor Loading…
3
[logging] Publish the training loop phase as a Prometheus gauge
#1923 opened Jul 17, 2026 by eicherseiji Contributor Loading…
4
[tinker] Fix per-tenant blocking on forward/forward_backward calls
#1920 opened Jul 17, 2026 by kailash109 Loading…
3
[feat] Adding rollout router replay (R3) on tinker path
#1919 opened Jul 17, 2026 by kailash109 Loading…
7
[GLM5.2] Use official IndexShare support
#1917 opened Jul 17, 2026 by yapdianang • Draft
perf(sample-support): add packed base64 transport
#1915 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
feat(fsdp): add bounded sampler-support replay
#1914 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
feat(megatron): add bounded sampler-support replay
#1913 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
refactor(generators): assemble routed-expert traces incrementally
#1912 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
refactor(inference): extract reusable RemoteInferenceGenerator
#1911 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
perf(r3): expand replay routes to local layers only
#1910 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
perf(r3): accelerate routed-expert transport with packed arrays
#1909 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
fix(r3): align routed-expert metadata and padding
#1908 opened Jul 16, 2026 by dyurk-lila Contributor Loading…
1
[fix] Render multimodal sample prompts under the base model (#1860)
#1907 opened Jul 16, 2026 by sunnyadn Loading…
1
2
[logging] Split rollout trajectory time into inference-engine wait vs env.step
#1900 opened Jul 14, 2026 by eicherseiji Contributor Loading…
7
FP8 KV-Cache Compatibility for Hybrid vLLM Models
#1899 opened Jul 14, 2026 by YJHMITWEB Loading…
@jinghanyao1-hub
2
FP8 RL Training and Rollout Weight Synchronization
#1898 opened Jul 14, 2026 by YJHMITWEB Loading…
@jinghanyao1-hub
3
[algorithm] Add REPO-R adaptive entropy loss
#1896 opened Jul 14, 2026 by erictang000 Collaborator Loading…
6
[deps] Make transformers/ml_dtypes overrides unconditional to fix macOS dev env
#1894 opened Jul 14, 2026 by kurtislin Contributor Loading…
5 of 6 tasks
Add AMD ROCm Docker image and Tinker training examples
#1892 opened Jul 14, 2026 by eddierichter-amd Loading…
19
Add bounded-memory training and colocation controls
#1890 opened Jul 13, 2026 by YJHMITWEB Loading…
@jinghanyao1-hub
3
[deps] bump megatron-bridge to fbf2d3 run_h100_gpu_ci Run H100 GPU CI run_train_megatron_gpu_ci_models run_train_megatron_gpu_ci
#1888 opened Jul 13, 2026 by erictang000 Collaborator Loading…
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.