BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//OneJoy//events//EN
BEGIN:VEVENT
UID:onejoy-event-21523@onejoy
DTSTAMP:20261002T225917Z
DTSTART:20260911T190000Z
DTEND:20260911T210000Z
SUMMARY:vLLM: LLM inference and serving
LOCATION:
DESCRIPTION:This session introduces vLLM\, an open-source library for LLM inference and serving. We will build an intuitive systems-level understanding of how vLLM approaches these production challenges\, from a token’s journey through prefill and decode to the scheduling and memory-management techniques that make high-throughput serving practical.\nStart exploring at vllm (https://docs.vllm.ai/en/latest/).\n\nSlides for past meetups posted: Github (https://github.com/YanXuHappygela/LLM-reading-group/tree/main)\n\nhttps://onejoy.io/event/21523
URL:https://onejoy.io/event/21523
END:VEVENT
END:VCALENDAR