OpenShift (vLLM) Meetup

The OpenShift Meetup team is excited to invite you to the inaugural in-person vLLM meetup in Melbourne hosted by Red Hat at the Melbourne Red Hat office.

This is your chance to connect with a growing community of vLLM users, developers, maintainers, and engineers from Red Hat. We'll dive deep into technical talks, share insights, and discuss our journey in optimizing LLM inference for performance and efficiency.

This is an in-person event only.

What to expect:
Technical insights
Networking with industry experts
Hands-on learning & demos

Agenda
5:30-6:00: Registration and Opening Remarks
6:00-6:30: Keynote: Turning GenAI Investments into Results: Why Inference Matters.
6:30-7:00: AI Inference
7:00-7:30: Intro to vLLM and it's techniques: Quantization, KV Cache, Paged-Attention, and Continuous Batching
7:30-8:00: vLLM Inference Demo – NVIDIA GPU Accelerator
8:00-8:30: Break
8:30-9:00: Hands-on Lab: vLLM Inference