BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Perplexity AI: Under the Hood of LLM Inference - Nandor Licker
DTSTART:20251013T120500Z
DTEND:20251013T125500Z
UID:TALK237178@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:Abstract: Perplexity is a search and answer engine which lever
 ages LLMs to provide high-quality citation-backed answers.\nThe AI Inferen
 ce team within the company is responsible for serving the models behind th
 e product\, ranging from single-GPU embedding models to multi-node sparse 
 Mixture-of-Experts language models.\nThis talk provides more insight into 
 the in-house runtime behind inference at Perplexity\, with a particular fo
 cus on efficiently serving some of the largest available open-source model
 s.\n\nBiography:Nandor Licker is an AI Inference Engineer at Perplexity\, 
 focusing on LLM runtime implementation and GPU performance optimization.\n
 \nRegister for the talk at the following link: https://luma.com/dx1ggxgk\n
 \n\nSome catering will be provided after the talk.
LOCATION:FW26\, William Gates Building
END:VEVENT
END:VCALENDAR