Fast AGI: Speculative Decoding

​​At the beautiful LMCache office, we are providing you with an amazing meetup about speculative decoding.

********************************
Agenda

​​Networking: 6:30 PM - 7:00 PM

​1. Talk: 7:00-7:30

​Title: Speculative Decoding in vLLM

​Speaker: Lily Liu

2. Panel Discussion 7:30-8:15
Lily Liu, Kuntai Du, Yihua Cheng

​***************************
Follow these two amazing projects:

vLLM: /vllm-project/vllm

LMCache: /LMCache/LMCache

*****************************
This webinar is ideal for infra developers, AI practitioners, and ML engineers who want to rapidly implement enterprise-grade agentic AI solutions within their organizations.