Search

99 results

Clear filters
  • OCT. 8, 2025 / Web

    Own your AI: Learn how to fine-tune Gemma 3 270M and run it on-device

    This guide shows you how to fine-tune the Gemma 3 270M model for custom tasks, like an emoji translator. Learn to quantize and convert the model for on-device use, deploying it in a web app with MediaPipe or Transformers.js for a fast, private, and offline-capable user experience.

    OYOAI_Metadata_RD2-V01
  • OCT. 7, 2025 / AI

    Building High-Performance Data Pipelines with Grain and ArrayRecord

    To avoid data bottlenecks when training large models, this guide introduces Grain and ArrayRecord for building high-performance data pipelines.

    The Agentic experience: Is MCP the right tool for your AI future?
  • OCT. 3, 2025 / AI

    Level Up Your Dev Game: The Jules API is Here!

    Google has released the Jules API, a new tool for developers to automate and integrate the software development lifecycle. The API is based on "Source," "Session," and "Activity" concepts, and Google has provided a quickstart guide to help developers begin using it.

    Thumb_API
  • OCT. 1, 2025 / AI

    Gemini for Home: Expanding the Platform for a New Era of Smart Home AI

    Google Home is enabling new Gemini-powered features for our partners’ devices and launching a new program to help them build the next generation of AI cameras.

    Geminicomingtohome_Hero
  • SEPT. 30, 2025 / AI

    Introducing Tunix: A JAX-Native Library for LLM Post-Training

    Tunix is a new JAX-native, open-source library for LLM post-training. It offers comprehensive tools for aligning models at scale, including SFT, preference tuning (DPO), advanced RL methods (PPO, GRPO, GSPO), and knowledge distillation. Designed for TPUs and seamless JAX integration, Tunix emphasizes developer control and shows a 12% relative improvement in pass@1 accuracy on GSM8K.

    Tunix logo
  • SEPT. 29, 2025 / AI

    Gemma explained: EmbeddingGemma Architecture and Recipe

    EmbeddingGemma, built from Gemma 3, transforms text into numerical embeddings for tasks like search and retrieval. It learns through Noise-Contrastive Estimation, Global Orthogonal Regularizer, and Geometric Embedding Distillation. Matryoshka Representation Learning allows flexible embedding dimensions. The development recipe includes encoder-decoder training, pre-fine-tuning, fine-tuning, model souping, and quantization-aware training.

    Building-2-banner
  • SEPT. 26, 2025 / AI

    Apigee Operator for Kubernetes and GKE Inference Gateway integration for Auth and AI/LLM policies

    The GKE Inference Gateway now integrates with Apigee, allowing enterprises to unify AI serving and API governance. This enables GKE users to leverage Apigee's API management, security, and monetization features for their AI workloads, including API keys, quotas, rate limiting, and Model Armor security.

    GfD-Apigee-IG-Blog
  • SEPT. 26, 2025 / AI

    Delight users by combining ADK Agents with Fancy Frontends using AG-UI

    The ADK and AG-UI integration enables developers to build interactive AI applications by combining a powerful backend (ADK) with a flexible frontend protocol (AG-UI). This unlocks features like Generative UI, Shared State, Human-in-the-Loop, and Frontend Tools, allowing for seamless collaboration between AI and human users.

    Screens-2-banner
  • SEPT. 26, 2025 / AI

    Your AI is now a local expert: Grounding with Google Maps is now GA

    Grounding with Google Maps in Vertex AI is now generally available, helping developers build factual and reliable generative AI applications connected to real-world, up-to-date information from Google Maps. This unlocks better, more personal results and is useful across industries like travel, real estate, devices, and social media.

    unnamed
  • SEPT. 25, 2025 / AI

    Continuing to bring you our latest models, with an improved Gemini 2.5 Flash and Flash-Lite release

    Google is releasing updated Gemini 2.5 Flash and Flash-Lite preview models with improved quality, speed, and efficiency. These releases introduce a "-latest" alias for easy access to the newest versions, allowing developers to test and provide feedback to shape future stable releases.

    Rev21Flash_Metadatal_RD2-V01