1. X
  2. NovaSky
Log inSign up
NovaSky
156 posts
Image
user avatar
NovaSky
@NovaSkyAI
Building SkyRL at @BerkeleySky Join the Slack community: join.slack.com/t/skyrl/shared…
Berkeley, California
github.com/NovaSky-AI/Sky…
Joined January 2025
18
Following
2,834
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    NovaSky
    @NovaSkyAI
    Feb 13
    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
    user avatar
    Tyler Griggs
    @tyler_griggs_
    Feb 13
    SkyRL now implements the Tinker API. Now, training scripts written for Tinker can run on your own GPUs with zero code changes using SkyRL's FSDP2, Megatron, and vLLM backends. Blog: novasky-ai.notion.site/skyrl-tinker 🧵
    Image
  • user avatar
    NovaSky
    @NovaSkyAI
    Apr 24
    Check out VLM training in SkyRL! SFT / multi-turn RL, LoRA / full-finetuning, tinker-compatible as well!
    user avatar
    Nithin Chalapathi
    @nithinch10
    Apr 24
    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:
    Image
  • user avatar
    NovaSky
    @NovaSkyAI
    Mar 22
    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!
    user avatar
    Aditya Soni
    @Aditya_Soni_8
    Mar 20
    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]
    Image
  • user avatar
    NovaSky
    @NovaSkyAI
    Feb 26
    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!
    user avatar
    Shiyi Cao
    @shiyi_c98
    Feb 26
    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
    Image
    Image
  • user avatar
    NovaSky
    @NovaSkyAI
    Feb 19
    Excited to see SkyRL being used by systems research to study how agentic RL workload can be optimized!! github.com/ThunderAgent-o…
    user avatar
    Hao Kang
    @GT_HaoKang
    Feb 17
    🔥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

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement