# Powering Open-Source AI at Unmatched Speed and Scale

**Customer:** Together AI

Together AI uses WEKA® NeuralMesh™ to reduce latency and deliver ultra-fast data access and scalable performance across its massive GPU-powered cloud environment.

[Together AI](https://www.together.ai/) provides high-performance infrastructure and tools for developers at scale.

With WEKA, Together AI can support the rapid growth and development of its industry-leading inference engine.

> At Together AI, we are obsessed with speed and efficiency. That’s why we built the Together Inference Engine that provides the fastest inference speeds in the industry. We are excited to leverage WEKA’s Augmented Memory Grid capability to reduce the time involved in prompt caching and improve the flexibility of leveraging this cache across multiple nodes— reducing latency and benefitting the more than 500,000 AI developers building on Together AI.
>
> — Ce Zhang, Chief Technology Officer • Together AI