Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore the latest innovations in Docker Model Runner through this 33-minute episode featuring Oleg Å elajev and Eric Curtin from the Docker Model Runner team. Discover how Docker Model Runner is revolutionizing local AI model deployment with multi-engine support for Llama.cpp and vLLM, expanded GPU acceleration including Vulkan and AMD support for various hardware setups, and OCI model packaging capabilities for seamless distribution through Docker Hub, GHCR, or private registries. Learn about the enhanced CLI experience with improved context retention and cancellation options, witness multimodal AI demonstrations running locally, and understand Docker Offload's cloud GPU integration while maintaining local workflow simplicity. Gain insights into how these developments enable developers to build, run, and scale AI workloads from fine-tuning small models to deploying multimodal applications at the edge, all while maintaining Docker's signature simplicity and open-source approach.
