Pinned
We are excited to announce that SkyRL now implements the Tinker API. Run Tinker training scripts on your own hardware with zero code changes.
Try it out today: novasky-ai.notion.site/skyrl-tinker
This post is from a protected account.
NovaSky
@NovaSkyAI
- Check out VLM training in SkyRL! SFT / multi-turn RL, LoRA / full-finetuning, tinker-compatible as well!SkyRL now supports end-to-end vision-language post-training, from SFT to agentic RL, and adds vision model support to SkyRL’s Tinker interface! Existing multimodal cookbooks, e.g. VLM classification, work out of the box:
- Great work from the @OpenHandsDev community and CMU! Open source SOTA on code localization via RL. Happy to see the beautiful reward curves trained with SkyRL!Can we train code agents to search relevant locations in a codebase only using a terminal? Introducing CodeScout: an effective RL recipe for code search 🚀 🏆 Outperforms 18x larger OSS LLMs 🔥 Comparable to proprietary LLMs 📈 SoTA on SWE-Bench Verified, Pro, & Lite 🧵 [1/N]
- We’ve been consistently surprised lately by how capable frontier models are at handling complex kernel implementation and system optimization. Check out this work as a step toward automating AI infrastructure building!Introducing our new work K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model — a new paradigm for automated GPU kernel generation, achieving SoTA results. 🔍 Big insight: Traditional methods treat LLMs as stochastic code generators inside heuristic loops — but
- Excited to see SkyRL being used by systems research to study how agentic RL workload can be optimized!! github.com/ThunderAgent-o…🔥Modifying 2 lines of code and get your agentic serving/rollout up to 3.9x faster losslessly! ⚡️Say hello to ThunderAgent, a fast, simple, and program-aware agentic Inference System. 🥇 We propose a program abstraction to schedule all GPU and CPU resources, the first
