ML 21885 1

Reduce LLM latency with prefix-aware routing on Amazon SageMaker Inference

When you build an application on top of a large language model (LLM), the prompt you send to the model typically has two parts. There’s a fixed part that sets up context (instructions, reference documents, conversation history) and a variable part that contains the actual user input. Take a customer service bot as an example. …

ML 21725 1

Deploying Qwen3.8-2.4T-A95B on Amazon SageMaker HyperPod with vLLM

On August 12, 2026, Alibaba’s Qwen team released Qwen3.8-2.4T-A95B. This is the first time a Qwen-Max-class model has been made available as open weights. With 2.4 trillion total parameters (95 billion activated per token), a hybrid linear-plus-full-attention architecture, and native context up to 262K tokens (extensible to 1M), Qwen3.8 targets the most demanding agentic and …

High Res Gartner EAIA Magic Quadrantmax 1000x1000 1

Google is a Leader in the 2026 Gartner® Magic Quadrant™ for Enterprise AI Assistants

We are excited to share that Gartner has named Google a Leader in its inaugural 2026 Magic Quadrant for Enterprise AI Assistants. In this comprehensive evaluation of top enterprise AI assistant vendors, Gartner placed Google in the Leaders quadrant for its evaluation across both Completeness of Vision and Ability to Execute. Gemini Enterprise helps organizations …

ML 21849 1

Take on your most ambitious work with GPT-6 Astra on Amazon Bedrock

GPT-6 Astra from OpenAI brings greater depth and judgment to your most demanding tasks and runs on the Amazon Bedrock inference engine built for high performance, security, and scale. Organizations are already running AI agents that write code, analyze data, and automate complex workflows at production scale on Amazon Bedrock. GPT-6 Astra raises the potential …

image1 9ZYjQgtmax 1000x1000 1

How KDDI built Buffmee, a faster, reliable consumer RAG app

When building consumer-facing generative AI applications,  balancing high generation quality with fast response times across diverse media types, can be challenging. KDDI, a major telecommunications carrier in Japan, tackled this challenge head-on when they developed Buffmee, their consumer Retrieval-Augmented Generation (RAG) app.   Buffmee is an interactive AI service built on the concept of ‘AI that …

ML 21164 1

Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore

This post shows how to deploy a multimodal WhatsApp ordering assistant built with Amazon Bedrock AgentCore and Amazon Nova 2. Many quick-service restaurants spread ordering across an app, a website, a phone line, and the counter. Each of those is a separate system to build and run. Each one also fragments the customer’s history, making …

1 Dual Write Architecturemax 1000x1000 1

Spanner migrations: Automating dual-write with Antigravity CLI for minimal disruption

When Google’s Finance Engineering team needed to modernize their legacy data layer, they chose Spanner, a globally distributed, strongly consistent, multi-model database with high availability capabilities. But migrating to Spanner without taking production services offline was a daunting engineering challenge: As the internal team responsible for the application, we needed to manually rewrite dual-write logic …

ML 21366 1

AI-driven development lifecycle using Amazon Bedrock AgentCore

Engineering teams adopting the AI-Driven Development Lifecycle (AI-DLC) with Amazon Bedrock AgentCore and coding agents like Kiro often struggle with the gap between conceptual frameworks and working code. Amazon Bedrock AgentCore is a service for building, connecting, and optimizing agents at scale with any framework or model. AI-DLC positions AI as a central collaborator across …

REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs

Most current vision-language-action (VLA) models—such as OpenVLA, π0, RT-2, and RDT-1B—are “monolithic.” This means they generate raw motor commands or very short sequences of actions, without organizing behaviors into reusable, well-defined abstractions. As a result, these models perform poorly on long-horizon (multi-step) tasks, and it’s difficult to interpret what they have learned. Existing approaches for …