⚡️ FlashAttention-4: up to 1.3× faster than cuDNN on NVIDIA Blackwell →

Introducing Together AI's new look →

🔎 ATLAS: runtime-learning accelerators delivering up to 4x faster LLM inference →

⚡ Together GPU Clusters: self-service NVIDIA GPUs, now generally available →

📦 Batch Inference API: Process billions of tokens at 50% lower cost for most models →

🪛 Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts →

Events / NVIDIA GTC 2026
diamond sponsor

Together AI at NVIDIA GTC

  • Mar 16-19, 2026
  • San jose, ca

Everything that happened at GTC, all in one place.

Get recaps and replays from the show floor and beyond, including on-demand sessions and everything we shipped for developers, engineers and researchers building on the AI Native Cloud.

Crowd of people gathered at the together.ai booth with colorful illuminated arches and signage about AI cloud computing, inference, model shaping, and research.

On-demand sessions from NVIDIA GTC

March 17
March 18
  • talk
    Hard-won lessons from production inference at scale
    Ce Zhang
    Co-founder & CTOTogether AI
    Yuchen Wu
    EngineerCursor
    Cyrus Lalkaka
    Strategic Account ExecutiveTogether AI
    Three men standing on stage at NVIDIA GTC event with audience in front.
  • talk
    NVIDIA GTC Studio: With insights from Together AI
    Ce Zhang
    Co-founder & CTOTogether AI
    Tiffany Janzen
    Foundertiffintech
    Two people sitting in chairs facing each other, speaking into microphones, with a small table holding plants and two mugs between them.
  • talk
    Engineering real-world LLM inference: Bridging open-source and production systems
    Yineng Zhang
    Senior Director, InferenceTogether AI
  • talk
    Build trust and discovery through open- source AI in research
    Percy Liang
    Co-FounderTogether AI
    Hanna Hajishirzi
    Professor, Sr. Director NLPAI2
    Three men standing on stage at NVIDIA GTC event with audience in front.
  • talk
    Under the hood of building and scaling 
AI-native applications
    Charles Zedlewski
    cpoTogether AI
    Alan Yiu
    VP of ProductDecagon
    Man speaking at an NVIDIA GTC event, standing next to a logo on a white backdrop.

GTC-related news & announcements

Company

What is an AI Native Cloud?

AI-native companies need infrastructure built for models, not legacy workloads. Learn what defines an AI Native Cloud and why it matters for the next platform shift.

Research

Inside the Together AI kernels team

The team behind FlashAttention and ThunderKittens — how Together AI's kernel researchers close the gap between GPU hardware and production AI.

Missed us at GTC? Scroll through 
some of the highlights

Logo of together.ai with three interconnected colorful circles in purple, magenta, and orange to the left.

00:00

/

00:00