Together AI Releases Aurora: Open-Source RL Framework for Self-Improving Speculative Decoding

Jul 11, 2026

Together AI has introduced Aurora, an open-source reinforcement learning framework that transforms speculative decoding into a self-improving system. Aurora learns from every request it serves and achieves a 1.25x speedup over a well-trained static speculator.

Why it matters: Aurora enables LLM inference to continuously improve without manual retuning, potentially reducing latency and cost in production.

Full story at: Together AI Blog ↗