Together AI 发布自适应投机系统 ATLAS，推理速度大幅提升

AI 摘要

Together AI 推出了自适应学习投机系统 ATLAS，这是首个无需手动调优即可自动提升推理性能的投机解码系统。ATLAS 结合静态和自适应投机器，根据实时流量动态调整，在 DeepSeek-V3.1 上达到 500 TPS，在 Kimi-K2 上达到 460 TPS，比标准解码快 2.65 倍。该系统旨在解决静态投机器在多变工作负载下性能下降的问题，并已集成到 Together Turbo 中。

正文节选

At Together AI, the AI Native Cloud, we’re obsessed with performance. Making large language models faster, cheaper, and more efficient is not a one-trick problem — it requires optimizing along multiple axes. That is the philosophy behind Together Turbo, our suite of inference innovations that draw from research in algorithms, architectures, and modeling recipes. We’re excited to introduce the AdapTive-LeArning Speculator System (ATLAS), the first speculator of its kind that gives automatic perfo

发布时间：—

抓取时间：2026-08-02 00:28

来源机构：Together AI