Open-Source Inference Engineering for the Agentic Era
SponsorWorkshop trackconfirmed
Open-Source Inference Engineering for the Agentic Era
- Day
- Day 1 — Workshop Day
- Time
- 9:00am-11:00am
- Room
- Track 8
- Track
- Workshops Day 1
Accessible with the Engineering + Workshops pass and above.
About this session
Agentic coding workloads demand long contexts, multi-turn conversations, and throughput at a scale that most inference engines weren't built for. TokenSpeed is a new open-source engine purpose-built for this regime, built collaboratively by NVIDIA DevTech, AMD Triton, Qwen Inference, Together AI, and others. In this 2-hour hands-on workshop, Together Inference Research Engineers and a TokenSpeed co-creator will cover TokenSpeed architecture, deploying your first model, optimizing for agentic workloads, kernel and hardware tuning, and throughput/latency trade-offs.
