BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//TKX3QE
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-W98LCM@pretalx.devconf.info
DTSTART;TZID=EST:20260924T100000
DTEND;TZID=EST:20260924T112000
DESCRIPTION:Llm-d gives you the ability to deliver generative AI capability
  at scale at a higher density and performance given the same amount of har
 dware\, if supported by the architecture.\n\nTechnical attendees will lear
 n not only how to perform these actions\, but how to demonstrate their val
 ue through repeatable steps that show measurable improvements in throughpu
 t and latency. Specifically\, attendees will get hands on experience with:
 \n- Intelligent Inference Scheduling and its benefits achieving your SLOs 
 on a limited hardware\n- Designing\, running\, and understanding benchmark
 s with GuideLLM\n\nAttendees will also gain an understanding of Prefill/De
 code disaggregation for scaling phases of inference independently and Wide
  Expert Parallelism for MoE models like DeepSeek R1\, understanding how to
  serve the largest models at scale.
DTSTAMP:20260924T235733Z
LOCATION:107 (Capacity 20)
SUMMARY:Hands-On llm-d: Building High-Performance AI Inference at Scale - C
 hristopher Nuland
URL:https://pretalx.devconf.info/devconf-us-2026/talk/W98LCM/
END:VEVENT
END:VCALENDAR