NVIDIA NVIDIA
June 30, 2026

How Together AI Uses NVIDIA's Full Stack to Deliver AI Responses in Under 100ms

Together AI's Dan Fu, Vice President of Kernels, explains how Together AI leverages NVIDIA GPUs to deliver AI responses in under 100 milliseconds while achieving some of the industry's lowest token...

Together AI's Dan Fu, Vice President of Kernels, explains how Together AI leverages NVIDIA GPUs to deliver AI responses in under 100 milliseconds while achieving some of the industry's lowest token costs. From developing a megakernel that fits an entire model into a single CUDA kernel to powering real-time voice agents that return their first 64 words in under 100 milliseconds, Together AI is focused on minimizing latency at every layer of the AI stack.
446

Comments 0

Replying to
5000 max

Be the first to comment!

This website uses cookies
This website uses cookies.
To maintain our services, we use cookies. They allow us to personalize ads, analyze our traffic, and provide social media features.

Customize your preferences

Select the cookies you accept: