Workflow
Semiconductors & AI Infrastructure
icon
Search documents
vLLM in 2026: Challenges and Optimizations
AMD· 2026-08-14 12:21
Thank you so much. Thank you for showing up and coming with me to join this session. And what we plan to do today, over the next 20 minutes, is to really cover.there's a lot to cover about inference, but I would like to sort of tell you a little bit about how we approach open source inference from vLLM, which is the inference engine that lets you run any large language model on data center hardware. And really there to. hopefully this will be a start and a spark of discussion and inspiration for you all.And ...
Building Next-Gen AI Infrastructure: Scaling Enterprise LLM Serving with RadixArk
AMD· 2026-08-14 12:21
Thank you, everyone, for joining this session. I'm very excited to talk about the SGLN Miles, two open source frameworks that we have spent time building on this that aim to help you build frontier AI infrastructure. Let's start with, I mean, what is SGLN.Some of you might already heard of and maybe are using it. It's an open source framework for inference and has been widely adopted in production. People use it to serve open source models in many companies across all the categories.It aims for a target for ...