AgendaSession Abstracts | Speaker Bios 10:00 – 10:30
30 mins
Registration 10:30 – 10:40
10 mins
Welcome Speech Jiaju Zhang — Chief Architect, Red Hat 10:40 – 11:10
30 mins
Getting started with vLLM: The leading open-source LLM inference engine for Private AI Christopher Nuland — Principal Technical Marketing Engineer, AI BU, Red Hat Peter Ho — Senior Solution Architect, Red Hat 11:10 – 11:40
30 mins
Multi-modal inference and deployment using vLLM Cyrus Leung — Multi-Modality Co-Lead, vLLM Team 11:40 – 12:10
30 mins
LLM inference on AMD GPUs: A Technical Deep Dive Haichen Zhang — Senior PM, AI Engineering, AMD 12:10 – 12:15
5 mins
Group Photo 12:15 – 13:15
60 mins
AMD Hands-on Workshop: Minimax M2 Agent Tutorial Haichen Zhang — Senior PM, AI Engineering, AMD 13:15 – 14:15
60 mins
Lunch & Networking 14:15 – 14:45
30 mins
From Offline to Online Inference: Why Serving Is Hard—and How vLLM Helps Henry Wong — Data Scientist, Python User Group HK 14:45 – 15:15
30 mins
Deep Adaptation and Engineering Practice of vLLM on MetaX GPU William Chan — Software Expert, AI Solutions, MetaX 15:15 – 15:45
30 mins
Zebin Li — Software Engineer, MiniMax 15:45 – 16:15
30 mins
vLLM-Omni: Easy, Fast, and Cheap Omni-Modality Model Serving Han Gao — vLLM-Omni Core Maintainer 16:15 – 17:00
45 mins
Networking 17:00
Event End Subject to change. |
|
|