InfiniAI Lab releases AstraFlow, an open-source reinforcement learning engine that delivers 2.7 times faster geo-distributed multi-policy LLM training via dataflow abstractions and 1.1 percent sparse weight transfers

Align with how @cursor_ai has done its RL stage — Astraflow is a new RL engine that enables asynchronous, heterogeneous, and geo-distributed RL in a native way through dataflow abstraction~ Like @FireworksAI_HQ’s sparse RL transfer design, it syncs only ≤1.1% of model weights — making remote rollout lightweight and efficient. Check it out!!!