World Congress 2024 Aug 20, 2024 Session details

Containers and Kubernetes made easy: Deep dive into Podman Desktop and new AI capabilities

Stevan Le Meur

Eliminate local-to-production Kubernetes friction using Podman Desktop. Learn to build multi-container pods and securely prototype large language models locally without compromising data privacy.

Pause
Mute Enter Fullscreen
#1 about 2 min

Podman Desktop adoption and project milestones

How community feedback and open-source contributions established continuous container development milestones during the project's first year.

#2 about 5 min

Architecture and security benefits of the Podman engine

How a daemonless system architecture enables rootless containers and secures non-root enterprise environments.

#3 about 5 min

Addressing local development challenges with Podman Desktop

Overcoming discrepancies between local developer setups and live Kubernetes environments with intuitive container management.

#4 about 8 min

Building and running multi-container applications locally

Building multi-stage Python and Redis containers via the desktop user interface without complex command line operations.

#5 about 1 min

Networking containers together using Kubernetes pods

Combining individual containers into a pod to share localhost networking and mirror actual Kubernetes environments.

#6 about 2 min

Deploying local container pods to Kubernetes clusters

Setting up a local control plane via Kind or Minikube to transition pods straight into Kubernetes deployments.

#7 about 4 min

Simplifying generative AI adoption with Podman AI Lab

Providing local sandbox environments to test and run generative AI models securely without cloud provider lock-in.

#8 about 4 min

Running local AI models with containers and endpoints

Setting up a quantized GGUF model via a local endpoint to safely test chat interactions and integrate language models.

#9 about 3 min

Building retrieval-augmented generation applications with vector databases

Utilizing a distributed vector database and an inference server to enrich foundation models with external documents.

#10 about 2 min

Enabling experimental GPU acceleration for local containers

Applying hardware acceleration passthrough for container environments to optimize model inference processing speeds.

#11 about 2 min

Future roadmap for the AI recipes catalog and extensions

Upcoming features for local model fine-tuning along with specific container extensions for platform compatibility.

Matching moments

3:11 min

Building local containerized models with Podman AI Lab

Cedric Clyburn Cedric Clyburn · WWC 2024

2:20 min

Running an AI model locally using Podman AI Lab

Cedric Clyburn Cedric Clyburn +1 · WWC 2025

1:40 min

Managing containerized infrastructure with Podman Desktop

Cedric Clyburn Cedric Clyburn +1 · WWC 2025

5:11 min

Developing a containerized AI code assistant locally

Cedric Clyburn Cedric Clyburn +1 · WWC 2025

3:31 min

Practical learnings from deploying containerized AI solutions

Sebastian Rhode Sebastian Rhode · WWC 2024

2:31 min

Integrating generative AI into cloud-native applications

Cedric Clyburn Cedric Clyburn · WWC 2024

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

Run your agents in Kubernetes: Build once, deploy anywhere. But really?

Michal Salanci

Senior Systems Engineer at ESET Cybersecurity

Michal Salanci
Open session

World Congress 2026 North America

rm -rf: Horror Stories From Unsandboxed AI Agents (and How Docker Fixes This)

Rishab Kumar

Staff Developer Evangelist @ Twilio

Rishab Kumar
Open session

World Congress 2026 North America

Stop Running Mystery Meat in Production

Jeroen van Erp

Technical Advocate @ SUSE

Jeroen van Erp
Open session

World Congress 2026 North America

Testing AI Workflows Locally with Testcontainers

Anna Chernyshova

Sr Solutions Engineer @ Docker

Anna Chernyshova
Open session

World Congress 2026 North America

Trust, But Verify: Continuous GPU Validation at Scale

Kyle Bell

VP of AI @ TensorWave

Kyle Bell