Building real-world on-device AI with LiteRT and NPU
markdown APRIL 23, 2026 Users benefit from instant AI features like real‑time video effects, ASR, and motion capture in their mobile apps. However, for develope...
markdown APRIL 23, 2026 Users benefit from instant AI features like real‑time video effects, ASR, and motion capture in their mobile apps. However, for develope...
AI agents are transitioning from experimental scripts to production services. But while models get smarter, the infrastructure required to build, evaluate, and...
New Post-Training Capabilities MaxText has introduced new support for Supervised Fine‑Tuning SFT and Reinforcement Learning RL on single‑host TPU configuration...
Overview The blog post outlines the transition of a brittle sales research prototype into a robust production agent using Google’s Agent Development Kit ADK. B...
A2UI v0.9 introduces a framework-agnostic standard designed to help AI agents generate real-time, tailored UI widgets using a company’s existing design system....
LiteRT is a production-ready framework designed to help mobile developers unlock the power of Neural Processing Units NPUs, overcoming the performance and batte...
APRIL 29, 2026 Today, we are announcing a major performance boost for AI/ML workloads using the PyTorch ecosystem on Google Cloud. By integrating Rapid Storage,...
APRIL 15, 2026 Subagents allow Gemini CLI to delegate complex, repetitive, or high-volume tasks to specialized expert agents. Each subagent operates within its...
Researchers at UCSD have successfully implemented DFlash, a block-diffusion speculative decoding method, on Google TPUs to bypass the sequential bottlenecks of...
Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production‑grade AI agent deployment. Th...
Introduction In the rapidly evolving landscape of large language models LLMs, pre‑training is only the first step. To transform a base model into a specialized...
The transition from a brittle sales‑research prototype to a production‑ready AI agent was achieved by applying a set of concrete engineering practices. Below ar...
Overview A2UI v0.9 introduces a framework‑agnostic standard designed to help AI agents generate real‑time, tailored UI widgets using a company’s existing desig...
Google has announced the general availability of Gemini Embedding 2, a unified model that maps text, images, video, audio, and documents into a single semantic...
LiteRT is a production‑ready framework designed to help mobile developers unlock the power of Neural Processing Units NPUs, overcoming the performance and batte...
Overview The post describes how a fragile sales‑research prototype was transformed into a production‑ready AI agent using Google’s Agent Development Kit ADK. B...
AI agents are transitioning from experimental scripts to production services. While models get smarter, the infrastructure required to build, evaluate, and depl...
New Capabilities MaxText has introduced new support for Supervised Fine‑Tuning SFT and Reinforcement Learning RL on single‑host TPU configurations, leveraging...
markdown April 29, 2026 Today we are announcing a major performance boost for AI/ML workloads using the PyTorch ecosystem on Google Cloud. By integrating Rapid...
Overview A2UI v0.9 introduces a framework‑agnostic standard designed to help AI agents generate real‑time, tailored UI widgets using a company’s existing desig...
Overview The blog post outlines the transition of a brittle sales research prototype into a robust production agent using Google’s Agent Development Kit ADK. R...
LiteRT is a production‑ready framework designed to help mobile developers unlock the power of Neural Processing Units NPUs, overcoming the performance and batte...
AI agents are transitioning from experimental scripts to production services. While models get smarter, the infrastructure required to build, evaluate, and depl...
In the rapidly evolving landscape of large language models LLMs, pre‑training is only the first step. To transform a base model into a specialized assistant or...
Overview A2UI v0.9 introduces a framework‑agnostic standard designed to help AI agents generate real‑time, tailored UI widgets using a company’s existing desig...
'APRIL 23, 2026
markdown April 29, 2026 Today we are announcing a major performance boost for AI/ML workloads using the PyTorch ecosystem on Google Cloud. By integrating Rapid...
Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production‑grade AI agent deployment. Th...
APRIL 16, 2026 In the rapidly evolving landscape of large language models LLMs, pre‑training is only the first step. To transform a base model into a specialize...
'APRIL 21, 2026
Overview LiteRT is a production‑ready framework designed to help mobile developers unlock the power of Neural Processing Units NPUs, overcoming the performance...
Overview Google has announced the general availability of Gemini Embedding 2, a unified model that maps text, images, video, audio, and documents into a single...
markdown April 15, 2026 Subagents in Gemini CLI Subagents let the Gemini CLI delegate complex, repetitive, or high‑volume tasks to specialized expert agents. Ea...
AI agents are transitioning from experimental scripts to production services. While models get smarter, the infrastructure required to build, evaluate, and depl...
In the rapidly evolving landscape of large language models LLMs, pre‑training is only the first step. To transform a base model into a specialized assistant or...
'APRIL 21, 2026
LiteRT is a production-ready framework designed to help mobile developers unlock the power of Neural Processing Units NPUs, overcoming the performance and batte...
Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production‑grade AI agent deployment. Th...
In the rapidly evolving landscape of large language models LLMs, pre‑training is only the first step. To transform a base model into a specialized assistant or...
Overview The blog post outlines the transition of a brittle sales‑research prototype into a robust production agent using Google’s Agent Development Kit ADK. K...
Overview The post describes how a fragile sales‑research prototype was transformed into a production‑ready AI agent using Google’s Agent Development Kit ADK. B...
LiteRT is a production‑ready framework designed to help mobile developers unlock the power of Neural Processing Units NPUs, overcoming the performance and batte...
April 15, 2026 Subagents allow Gemini CLI to delegate complex, repetitive, or high‑volume tasks to specialized expert agents. Each subagent operates within its...
Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production‑grade AI agent deployment. Th...
New Post-Training Capabilities MaxText has introduced new support for Supervised Fine-Tuning SFT and Reinforcement Learning RL on single-host TPU configuration...
A2UI v0.9 introduces a framework‑agnostic standard designed to help AI agents generate real‑time, tailored UI widgets using a company’s existing design system....
'April 15, 2026
'APRIL 23, 2026