{"id":"tp-31223","type":"article-newspaper","title":"NVIDIA, Princeton Lab Introduce ReplaySSM for Faster AI Decoding","author":"Simon Yoon","publisher":"TOKENPOST Inc.","url":"https://www.tokenpost.com/news/technology/31223","datePublished":"2026-10-13T14:22:38.000Z","dateModified":"2026-10-13T14:22:38.000Z","language":"en","abstract":"The method accelerated full decode steps by up to 1.47× and reached 2.10× speculative-serving throughput under specified test conditions.","section":"Technology","references":[]}