Dev Radar
Support
LiveUpdated 2026-09-20 16:47 UTC

🚀 New blog: Cosmos3 in RLinf: 3.33× End-to-End Evaluation Throughput with SGLang

🚀 New blog: Cosmos3 in RLinf: 3.33× End-to-End Evaluation Throughput with SGLang RLinf is an open-source framework…

This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.

🚀 New blog: Cosmos3 in RLinf: 3.33× End-to-End Evaluation Throughput with SGLang RLinf is an open-source framework designed for embodied intelligence & AI agents. It now supports Cosmos3 from fine-tuning to robot evaluation. With SGLang inference support, we deliver 3.33× end-to-end evaluation throughput Highlights: - SGLang batches inference for 128 parallel environments on 8 GPUs. Covering 500 episodes of the full LIBERO-10 evaluation. - RLinf overlaps CPU simulation with GPU inference to reduce waiting between stages. Thanks to the RLinf team for the integration! Read the full blog below

Posted by LMSYS Org (17.4k followers) 1 h ago · 6 likes · 476 views · view the original post on X. Kept by the Dev Radar as AI dev tools.

More dev work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.5k posts from 4.9k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 16:47 UTC. Full method.