BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//EACXYX
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-DQDEES@pretalx.com
DTSTART;TZID=CET:20260415T101500
DTEND;TZID=CET:20260415T104500
DESCRIPTION:What if you could run real data/ML workflows right in your brow
 sers - sandboxed\, with no installation or sending your data anywhere? Suc
 h an approach would have tons of benefits: it is easy to distribute\, safe
 r by default\, and can scale almost infinitely with virtually no infrastru
 cture costs. \n\nThis talk is a pragmatic overview of the current in-brows
 er ML stack. We’ll cover what  workflows are realistic today (from train
 ing of traditional ML models to on-device LLM inference)\, how packaging/l
 oading works\, and the constraints one should be aware of. By the end of t
 he talk you will have a clear sense of when in-browser ML is a good fit\, 
 and when it isn’t.
DTSTAMP:20260412T141833Z
LOCATION:Platinum [2nd Floor]
SUMMARY:State of In-Browser ML: WebAssembly\, WebGPU\, and the Modern Stack
  - Oleh Kostromin\, Iryna Kondrashchenko
URL:https://pretalx.com/pyconde-pydata-2026/talk/DQDEES/
END:VEVENT
END:VCALENDAR