Keynote: Accelerating GenAI Adoption with Containers: Unleashing AI/ML Development...
summary
Claims containers speed GenAI adoption by giving isolated reproducible environments and by packaging LLM tools and functions inside images. Demonstration shows a VS Code co‑pilot extension that analyzes a repo, calls LLMs with system prompts, generates Dockerfiles and uses Docker Scout to pick lower‑vulnerability base images. Mentions integrations with NVIDIA AI Workbench and Hugging Face Hub, recommends decomposing into small components, enforcing least privilege per container, and adding retries and durable execution for reliability. Works as described in the prototype demo.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 0:19What is helpful to think about
- 1:33How containers fit in
- 2:51Demo
- 4:48Key takeaways
- 5:33Conclusion
- 6:24Outro
related talks
28mContainers: the Last Opportunity to Make Reproducible AI
15mKeynote: From Platforms to AI Factories. Has Kubernetes Solved It?
25mBuilding AI Workflows: From Local Experiments To Serving Users
37mAI Lab Recipes: Cooking up AI Applications on your Laptop
07mEnter the Machines: Reducing Friction in Cloud Native using AI
47mEmbedding AI: Don’t Burn Your Fingers in the Heat of the AI revolution
30mDeveloper Productivity for GenAI Apps
33mThe Future of Developer Experience with GenAI: Driving Engineering Excellence