BEGIN:VCALENDAR
VERSION:2.0
PRODID:talks.ox.ac.uk
BEGIN:VEVENT
SUMMARY:Strachey Lecture with Professor Ion Stoica: An AI stack: from scal
 ing AI workloads to evaluating LLMs - Professor Ion Stoica (UC Berkeley)
DTSTART;VALUE=DATE-TIME:20260203T150000Z
DTEND;VALUE=DATE-TIME:20260203T160000Z
UID:https://talks.ox.ac.uk/talks/id/a151f861-e0c3-4a25-8ef6-ba888786d590/
DESCRIPTION:Large language models (LLMs) have taken the world by storm\, e
 nabling new applications\, intensifying GPU shortages\, and raising concer
 ns about the accuracy of their outputs. In this talk\, I will present seve
 ral projects I have worked on to address these challenges. Specifically\, 
 I will focus on Ray\, a distributed framework for scaling AI workloads\, v
 LLM and SGLang\, two high-throughput inference engines for LLMs\, and LMAr
 ena\, a platform for accurate LLM benchmarking. I will conclude with key l
 essons learned and outline directions for future research.\n\nProfessor Io
 n Stoica is a Professor in the Electrical Engineering and Computer Science
  Department at the University of California\, Berkeley\, and holds the Xu 
 Bao Chancellor Chair. He is the Director of the Sky Computing Lab\, and th
 e Executive Chairman and Co-founder of Databricks\, and Anyscale. Professo
 r Stoica's current research focuses on AI systems and cloud computing. His
  work includes open-source projects vLLM\, SGLang\, Chatbot Arena\, SkyPil
 ot\, Ray and Apache Spark. He is a Member of the National Academy of Engin
 eering\, an Honorary Member of the Romanian Academy\, and an ACM Fellow.\n
 Speakers:\nProfessor Ion Stoica (UC Berkeley)
LOCATION:University Museum of Natural History\, Parks Road OX1 3PW
TZID:Europe/London
URL:https://talks.ox.ac.uk/talks/id/a151f861-e0c3-4a25-8ef6-ba888786d590/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Strachey Lecture with Professor Ion Stoica: An AI stack: 
 from scaling AI workloads to evaluating LLMs - Professor Ion Stoica (UC Be
 rkeley)
TRIGGER:-PT1H
END:VALARM
END:VEVENT
END:VCALENDAR