BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconhk2024//speaker//TWFLNL
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
DTSTART:20231117T000000
TZNAME:HKT
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:[Sponsored Keynote] Large Language Models Optimization with Python
  - Haowen Huang
DTSTART;TZID=Asia/Hong_Kong:20241116T103000
DTEND;TZID=Asia/Hong_Kong:20241116T110000
DTSTAMP:20260817T233804Z
UID:pretalx-pyconhk2024-W9X8DD@pretalx.com
DESCRIPTION:This talk will cover various aspects of optimizing Large Langu
 age Models (LLMs) with Python\, including quick start\, availability optim
 ization\, and throughput optimization. Explore cutting-edge techniques inv
 olved in areas such as model compilation\, model compression\, model infer
 ence batching\, distributed training\, and Large Model Inference (LMI) con
 tainers. Discover practical examples of optimizing some open-source models
  using techniques like LMI containers\, Low-Rank Adaptation (LoRA)\, Fully
  Sharded Data Parallelism (FSDP)\, Paged Attention\, Rolling Batch\, and m
 ore.
LOCATION:LT9
URL:https://pretalx.com/pyconhk2024/talk/W9X8DD/
END:VEVENT
END:VCALENDAR