Skip to content
View original post on X: SGLangOfficial
Published
12/100

SGLang and Miles host a reinforcement learning training session with NVIDIA

AISGLang invites developers to a live session on running a reinforcement learning training loop with NVIDIA, using SGLang for rollout generation and Miles for policy training. The session covers live weight syncing between the two systems and engineering choices for faster, more stable RL training, with a path to larger models and more complex tasks.
SGLangVerified on XOfficial
@sgl_project
View on X

Part of a thread · earlier post

Run a real reinforcement learning training loop with @NVIDIAAI and the latest SGLang + Miles!

Use SGLang to generate rollouts, Miles to train the policy, and live weight syncing to connect them. Learn the engineering choices that make RL training faster and more stable, then explore how to scale the same workflow to larger models and more complex tasks.

Reserve your spot: https://luma.com/o53t6tvs

🧵 2/7

Source details

SGLang · x.comPublished · added here

Original title: Run a real reinforcement learning training loop with @NVIDIAAI and the latest SGLang + Miles!

Topics

Deployment & engineeringData & training

Tags

#Other