BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pycon-lithuania-2024//speaker//HGUBXP
BEGIN:VTIMEZONE
TZID:Europe/Vilnius
BEGIN:DAYLIGHT
DTSTART:20230406T000000
TZNAME:EEST
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T040000
RDATE:20241027T040000
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T040000
RDATE:20250330T040000
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Transcend the Knowledge Barriers in RAG: Setup\, Chat State\, and 
 More - Isaac Chung
DTSTART;TZID=Europe/Vilnius:20240405T113000
DTEND;TZID=Europe/Vilnius:20240405T115500
DTSTAMP:20260817T113057Z
UID:pretalx-pycon-lithuania-2024-HFXHRV@pretalx.com
DESCRIPTION:Developer tools power many LLM-based chat and Retrieval Augmen
 ted Generation applications today. However\, there is a non-trivial knowle
 dge barrier for entrants that could hinder developer experience. Our discu
 ssion intends to offer actionable insights into building and maintaining g
 enerative AI solutions in a secure and economical way\, thereby improving 
 the developer experience in this Generative AI wave.
LOCATION:Room 228
URL:https://pretalx.com/pycon-lithuania-2024/talk/HFXHRV/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Speed up open source LLM-serving with llama-cpp-python - Isaac Chu
 ng
DTSTART;TZID=Europe/Vilnius:20240405T150000
DTEND;TZID=Europe/Vilnius:20240405T152500
DTSTAMP:20260817T113057Z
UID:pretalx-pycon-lithuania-2024-DHBLXW@pretalx.com
DESCRIPTION:Large language models (LLMs) often require huge compute resour
 ces to serve. This is a common challenge for those who want to avoid shari
 ng their data with cloud API providers\, or to deploy their stack in air-g
 apped environments. We will take a look at how the open source llama-cpp-p
 ython library opens the door to lower hardware requirements and simplifies
  deployment significantly.
LOCATION:Room 111
URL:https://pretalx.com/pycon-lithuania-2024/talk/DHBLXW/
END:VEVENT
END:VCALENDAR