Together Compiler 发布：智能体自动为模型和硬件优化内核
Together 出了个自动优化 GPU 内核的智能体，在你已调优过的端点上还能把速度再提 12%-20%，生产响应时间砍近一半。
Together 推出 Together Compiler，用智能体针对用户的模型、硬件和流量持续优化 GPU 内核。该系统源自 FlashAttention、ThunderKittens、ThunderAgent 背后团队的成果。在其研究员已高度手动优化的 serverless 端点上，中位 TPS 提升 12% 到 20%。已有生产环境客户将响应与生成时间缩短约三分之一到近一半。
Introducing Together Compiler: agents that continually optimize kernels for your model, your hardware, and your traffic.
We built this to scale frontier research from the teams behind FlashAttention, ThunderKittens, ThunderAgent, and more to every customer deployment.
So far we're seeing: 👉 +12% to +20% median TPS on serverless endpoints our researchers had already heavily optimized by hand
👉 Customers in production cutting response and generation times by about a third to nearly half
Read the full story: https://t.co/wnRX2rWDnx
