Together AI 强调推理效率是 AI 生产系统的关键
原标题：Foundational research powering efficient inference at scale
AI 摘要
Together AI 在 NVIDIA GTC 2026 上强调推理效率对 AI 生产系统的重要性，指出推理成本占系统总成本的 80-90%。该公司通过 FlashAttention、ThunderKittens 和 Aurora 等开源技术优化推理性能，并利用 Blackwell 硬件实现全栈优化，帮助客户降低单位经济成本。文章还引用斯坦福 AI 指数，显示推理成本大幅下降，但总支出仍在上升。
正文节选
AI has spent years in the spotlight for training: the massive, GPU-intensive process of building models. But for most teams deploying AI today, ongoing inference costs are what actually shape their unit economics. Estimates put inference at 80-90% of the total lifetime cost of a production AI system, simply because it runs continuously across every user query, agent step, and API call. And while training is a bounded investment, inference scales with every new user and use case you ship. At NVID