Dynamo & Dine: High-performance LLM Inference with Baseten and NVIDIA Dynamo

​Join us for a hands-on technical workshop and Brazilian churrasco experience at Fogo de Chão.

​Discover how the world's largest AI inference workloads run at lightning speed on NVIDIA Dynamo, a distributed system for model serving.

​In this 1-hour workshop, Harry Kim (NVIDIA) and Philip Kiely (Baseten) will dive deep into system-level optimizations that turbocharge LLM inference at scale, including:

• ​KV-aware routing

• ​KV cache offloading

• ​PD disaggregation

​After the session and Q&A, stay for a churrasco lunch. Enjoy eight different meats, a fresh salad bar, and traditional sides.

​​If you’re an AI engineer in SF, don’t miss this technical workshop and chance to network with peers. Lunch is on Nvidia and Baseten!

​​​​​​✅ Follow Baseten on Twitter & Linkedin
✅ Follow Nvidia on Twitter & Linkedin

​***

​Workshop: 11:30AM-12:30PM
Lunch: 12:30PM