1 of 18

2 of 18

Yuan Tang

Principal Engineer at Red Hat

Project Lead at Argo and Kubeflow

Rajas Kakodkar

Senior Member of Technical Staff at VMware

Tech Lead at CNCF TAG Runtime

Welcome + Opening Remarks

3 of 18

4 of 18

5 of 18

Projects in the Cloud Native AI space

6 of 18

Cloud Native AI WG

7 of 18

8 of 18

CNCF End User Research Group

9 of 18

Nuances:

Can LLMs upgrade K8s control plane?

Can wasm be beneficial for inference at the edge?

How do go for a sustainable and responsible future of Cloud Native and AI

10 of 18

Code of Conduct

Remember the Golden Rule: Treat others as you would want to be treated - with kindness and respect

Scan the QR code to access and

review the CNCF Code of Conduct:

11 of 18

Captioning and Translation

ACCESSIBLE VIA WORDLY ON YOUR PERSONAL DEVICE

• Scan the QR code:

Choose your language, session ID will auto-populate, and select “Attend.”

• Captioning will begin when the session does.

12 of 18

Refreshments, Lunch, Reception

🍽️

Refreshments, snacks and lunch:

  • South Foyer on level 7.3, in front of E and S rooms
  • Additional lunch seating: level 7.1

CNCF-Hosted Co-Located Event reception:

  • Level 7.1 from 17:30-19:00 tonight!

13 of 18

Table Topics and Networking

Interested in discussing a particular topic during breaks and lunch?

Feel free to pick up table topic signs and markers located at the back of the room to facilitate your conversations!

14 of 18

Schedule Overview

15 talks from 9:15am to 5pm!

Batch/AI/ML workflow pipelines

Gen-AI at Scale: Simplifying Orchestration of Healthcare Applications Across Multi-Cluster Environment

Best practices for High Performance Computing (HPC) on Kubernetes

Kubernetes Empowered: A Journey with AI

Building Serverless AI Apps with Spin and WebAssembly

Best practices for MLOps (training+serving+pipelining)

Training and Optimisation of Large Transformer Models: an ATLAS and CERN use case

The Hitchhiker's Guide to Kubernetes Platforms: Don’t Panic, Just Launch!

Panel: Beyond the Clouds: Charting the course for AI in the CloudNative world

Best practices for LLM serving with DRA

Resource-Aware Scheduling for Production GenAI with RAG running on Multicluster Cloud Kubernetes

GPU and Hardware device management

Pods everywhere! InterLink: a Virtual Kubelet abstraction streamlining HPC resource exploitation

Effortless Scalability: Orchestrating Large Language Model Inference with Kubernetes

Cloud Native Networking For AI : Strengthen CNI For RDMA

ML applied FinOps

Make Descheduler Smarter and Safer: How we Apply Reinforcement Learning in Descheduling Strategies

Use cases for native kubernetes batch workloads

Efficient Multi-Cluster GPU Workload Management with Karmada and Volcano

Scale your Batch / Big Data / AI Workloads Beyond the Kubernetes Scheduler

Unleashing Kubernetes Intelligence - running k8sgpt utilizing your own fine-tuned LLM

15 of 18

Schedule Overview

16 of 18

Schedule Overview

17 of 18

Speaker Logistics

Speakers, please:

  • Get mic’d 5–minutes before your session (see AV team in the back of the room)
  • Be ready to hop on stage & hook up your laptops as soon as the previous speaker finishes

EMCs:

  • Rajas Kakodkar
  • Madhav Jivrajani
  • Amine Hilaly

18 of 18

Enjoy the day!