Keynote
summary
Overview of concrete launches and demos: announces MediaPipe Studio and high-level MediaPipe tasks for low-code mobile and web ML, a forthcoming Kaggle mobile computation and sign-language dataset, and the compiler-focused OpenXLA collaboration to optimize TensorFlow/PyTorch/Jax models for GPUs and TPUs. A new TensorFlow recommenders developer hub and a live demo of Simple ML for Sheets predicting penguin species from bill and flipper measurements with high-confidence scores show working end-to-end flows and practical deployment options.
AI-written summary · about
chapters (4)
related talks
36mKeynote! The opportunity for Android devs with AI and ML
01h 03mOpening Keynote
16mKeynote: An Open-Source Stack for AI Compute: Kubernetes + Ray + PyTorch + vLLM
16mKeynote: Building ML Systems Foundations at the Age of AI
22mKeynote: Kubeflow ML on Kubernetes
15mKeynote: Empowering Accessibility Through Kubernetes: The Future of Real-Time Sign Language Interpretation
02h 16mKeynote Day 2 - Full
16mKeynote: Accelerating AI/ML Development with Open Source Software
