BEGIN:VCALENDAR
VERSION:2.0
PRODID:Raspberry Pi Events
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260417T150407Z
UID:b24f8cd6-627d-4d09-b0f9-b16909543ba6
DTSTART:20241205T170000Z
DTEND:20241205T180000Z
CLASS:PUBLIC
DESCRIPTION:We will be demonstrating the inference acceleration of AI model
 s on Raspberry Pi using our AI inference engine\, Optimium. \n\nRaspberry 
 Pi has been used for various AI applications such as object detection for 
 delivery robots and LLMs including ChatGPT. Our team has conducted a varie
 ty of AI optimization projects to deploy computer vision models on Raspber
 ry Pi. For example\, we had a client who encountered a latency problem whi
 le deploying MediaPipe pose landmark model on Raspberry Pi 5. Additionally
 \, we successfully accelerated inference speed of the client's model on Ra
 spberry Pi using our own inference engine\, Optimium.\n\nOptimium is a nex
 t-generation inference optimization engine. It accelerates AI model infere
 nce on target hardware while maintaining accuracy and facilitates convenie
 nt AI model deployment across various hardware platforms using a unified t
 ool. **Most importantly\, it is highly optimized for Arm CPUs\, which Rasp
 berry Pi is utilizing**.\n\nIn the webinar\, we will be demonstrating the 
 optimization of an AI model for Raspberry Pi. We are going to run the AI m
 odel optimized by Optimium on Raspberry Pi and compare the result with tho
 se from models optimized using alternative inference engines.\n\nhttps://e
 vents.raspberrypi.com/community/532945aa-663b-4ae5-af26-e0ef855b0b96
SUMMARY:Boosting AI Capabilities on Raspberry Pi: AI Inference Optimization
  with Optimium
END:VEVENT
END:VCALENDAR