BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//speaker//9JAQBH
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-EXRZ3P@pretalx.devconf.info
DTSTART;TZID=EST:20260924T164000
DTEND;TZID=EST:20260924T171500
DESCRIPTION:Large Language Models are increasingly constrained by inference
  architecture rather than training. As workloads diversify\, traditional m
 onolithic serving stacks struggle with mixed latency targets\, long contex
 t prompts\, GPU memory pressure\, and inefficient batching. This talk pres
 ents two emerging patterns treating LLM inference as a distributed systems
  challenge.\n\n**Dynamic Prefill Decode (PD)** separates the compute-inten
 sive prefill phase from the memory-bound decode phase\, scaling each acros
 s specialized GPU pools to improve utilization and reduce tail latency.\n*
 *Semantic Routing** replaces static load balancing with inference-aware de
 cisions\, selecting the right model and infrastructure tier per request.\n
 \nWe explore tools like vLLM\, Ray Serve\, KServe\, and TensorRT-LLM.\nThe
  session includes a live demo showing semantic routing\, model selection\,
  latency differences\, and cost tradeoffs across multiple models.
DTSTAMP:20260727T165257Z
LOCATION:Ladd Room (Capacity 170)
SUMMARY:Emerging LLM Serving Architectures: Dynamic PD Disaggregation & Sem
 antic Routing - Ayushi Tiwari
URL:https://pretalx.devconf.info/devconf-us-2026/talk/EXRZ3P/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-KPN7LF@pretalx.devconf.info
DTSTART;TZID=EST:20260925T102000
DTEND;TZID=EST:20260925T105500
DESCRIPTION:Software Bill of Materials (SBOM) has become a foundational req
 uirement for software supply chain security. But modern applications incre
 asingly embed machine learning models\, datasets\, feature stores\, prompt
 s\, vector databases\, and training pipeline artifacts that traditional SB
 OMs were never designed to describe.\nThis talk explores extending SBOM co
 ncepts into an **AI Bill of Materials (AI-BOM)** that captures machine lea
 rning artifacts across the lifecycle.\n\nWe will examine:\n* Why SBOM alon
 e is insufficient for ML systems\n* What additional metadata is required f
 or AI systems\n* Mapping ML artifacts into CycloneDX/SPDX extensions\n* Pr
 ovenance\, reproducibility\, and compliance challenges\n* Security risks i
 n models\, datasets\, and prompt supply chains\n* How AI-BOM supports gove
 rnance\, auditability\, and responsible AI\nThe session includes a practic
 al architecture walkthrough and a focused demo showing how AI-BOM artifact
 s can be generated and integrated into existing DevSecOps workflows.
DTSTAMP:20260727T165257Z
LOCATION:106 (Capacity 45)
SUMMARY:Extending SBOM into AI-BOM: Managing ML Artifacts Beyond Traditiona
 l Software - Ayushi Tiwari
URL:https://pretalx.devconf.info/devconf-us-2026/talk/KPN7LF/
END:VEVENT
END:VCALENDAR