Keynote: New Advances for Cross-platform AI Applications in Docker
summary
Docker adds Docker support for WebGPU so container apps call host GPUs and accelerators through a single portable API, removing the need for separate vendor-specific GPU images. The demo uses WasmEdge LLMs in Rust to build portable inference binaries and shows Docker managing and orchestrating those Wasm-based LLMs with standard tooling. Claim is reproducible: one Rust binary runs on laptops, edge servers, and cloud nodes without distinct CUDA/ROCm builds, though integration work remains.
AI-written summary · about
chapters (6)
- 0:00Docker and AI integration
- 1:55Docker for diverse workloads
- 4:04Cross-platform AI apps
- 6:37AI model deployment
- 9:11Future Docker and AI
- 11:00Closing remarks
related talks
33mReady, Set, Go: WASM-Powered Containers Taking Your AI To New He...
31mBuild, Share, Run WebAssembly Apps Using the Docker Toolchain
05mKeynote: Wasm: A Revolution for Browsers, Containers, and the Cloud
41mCreating Versatile AI Agents Through Wasm+Rust
31mCloud Native WASM: What's All the Hype?
32mWebAssembly Based AI as a Service on the Edge with Kubernetes
25mLeveraging Wasm for Portable AI Inference Across GPUs, CPUs, OS & Cloud-Nativ...
40mWebAssembly for AI Infra : A Lightweight, Fast, and Secure Alternative Approach