Cloud Native Kuala Lumpur

Sustainability @ Cloud Native Kuala Lumpur Meetup - October 2024

Capacity: 500
in-person
Event date
Oct 21, 24
06:00 PM - 09:30 PM +08
Location
Microsoft Malaysia, Kuala Lumpur
About this event

Join us for the October 2024 edition of Cloud Native Kuala Lumpur Meetup for the Cloud Native Sustainability Week! And we are also celebrating 1 year of Cloud Native Kuala Lumpur, which means you can win special prizes! 🏆🏆🏆

Whether you are a software developer, SRE, cloud engineer or just interested in cloud native (and open source) concepts, this meetup is perfect for you.

This is also a great opportunity to network and connect with other professionals in the industry who are also passionate about cloud native. Don't miss out on the chance to learn from industry experts and discuss the latest advancements in cloud computing, software security, and more. RSVP now and secure your spot for the meetup!

NOTE: To avoid duplication, please RSVP only once, either here or in meetup page. And RSVP "yes" only if you're able to attend the meetup in-person. If you've RSVP-ed "yes" and couldn't make it to the meetup, please revert the RSVP to "no"

Sponsor: Microsoft

Co-sponsor: MoneyLion

Venue📍: Microsoft Malaysia @ Level 18, Menara Shell

Agenda
  1. 6:00 PM +08

    Arrival + Food

    in-person
  2. 7:30 PM +08

    Welcome note

    in-person

    Welcome note by the host

  3. 7:45 PM +08

    Look back: 1 year of Cloud Native Kuala Lumpur

    in-person
  4. 8:00 PM +08

    Sustainable AI Model Deployment with Kubernetes AI Toolchain Operator (KAITO) by Sujay Pillai

    in-person

    Join us for an insightful session on the Kubernetes AI Toolchain Operator (KAITO), an innovative open-source project designed to streamline AI model deployment on Kubernetes clusters. In this talk, we will explore how KAITO not only simplifies the deployment process but also promotes sustainability in AI operations.

    We will delve into the key features of KAITO, including:

    • Automated provisioning of GPU nodes based on model requirements, reducing idle resources and energy waste
    • Hosting large model images in the public, promoting the use of shared resources and reducing duplication.
    • Simplified onboarding of large AI inference models, enabling faster deployment and reducing the time-to-inference.
  5. 8:30 PM +08

    Lightning talk / Hiring

    in-person
  6. 8:45 PM +08

    Kepler & co. to the rescue of planet earth by Mageshwaran Sekar

    in-person

    In this session, we will look into Kepler (Kubernetes-based Efficient Power Level Exporter) and other cloud native tools to run a sustainable Kubernetes workloads

  7. 9:15 PM +08

    Quiz + Prize giveaway

    in-person

    Join the quiz and get a chance to win exciting giveaways

  8. 9:30 PM +08

    Free and easy. Mingle with attendees

    in-person
Speakers
Organizers
Gallery