BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pycon-lt-2023//talk//FYLU78
BEGIN:VTIMEZONE
TZID:Europe/Vilnius
BEGIN:DAYLIGHT
DTSTART:20220519T000000
TZNAME:EEST
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T040000
RDATE:20231029T040000
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T040000
RDATE:20240331T040000
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:ML model serving and monitoring with FastAPI - Monika Venčkauskai
 tė
DTSTART;TZID=Europe/Vilnius:20230519T110000
DTEND;TZID=Europe/Vilnius:20230519T112500
DTSTAMP:20260812T214224Z
UID:pretalx-pycon-lt-2023-FYLU78@pretalx.com
DESCRIPTION:MLOPs are a collection of practices that enable companies to b
 uild\, train\, deploy\, scale\, and operate models in production. Model se
 rving is one of the main MLOps tasks. There are multiple ways of running m
 odels in production these days: from open-source solutions to enterprise o
 fferings. However\, a custom-built serving solution in Python is the most 
 flexible option and can evolve together with your company's needs. \n\nThe
  quality of an ML service is defined by its speed\, accuracy\, and ability
  to deal with the load. FastAPI is faster than its predecessors. Also\, be
 ing a part of the Python ecosystem\, it supports all the main ML framework
 s. Moreover\, it supports the OpenAPI standard out of the box and makes da
 ta validation much easier. All of this and its concurrency capability make
  it a great choice for running ML models in production.
LOCATION:Saphire A - Python
URL:https://pretalx.com/pycon-lt-2023/talk/FYLU78/
END:VEVENT
END:VCALENDAR