Cloud Computing

Scaling LLM Inference: Multi-Node KV Cache Offloading with GKE & Managed Lustre

Significant contributors to this article include Sneha Aradhey, Software Engineer, Google Kubernetes Engine, and Michael MacDonald, Sr Software Engineer, Google Cloud Managed Lustre. Enterprise production environments are shifting to distributed, multi-node architectures to serve long-context window lengths and agentic AI. As these workloads scale, KVCaches often outgrow local CPU RAM and host SSD cache tiers. […]

Scaling LLM Inference: Multi-Node KV Cache Offloading with GKE & Managed Lustre Read More »

Conversational analytics in BigQuery brings trusted agentic reasoning to everyone

Businesses run on fast decisions, but the teams who hold the answers are often buried under a backlog of routine requests, leaving users waiting in line for insights they need now. Today, we are bringing Conversational Analytics in BigQuery to general availability, so both business and technical teams can query data, run multi-step analyses, and

Conversational analytics in BigQuery brings trusted agentic reasoning to everyone Read More »

Anomaly detection using dynamic thresholds and two-year-long alerts in Cloud Monitoring

Choosing the threshold of an alert policy can be a headache. You have to analyze historical data, aggregate it into semantically meaningful time series, and choose a threshold that matters. If the workload grows, your previously set static threshold might become too low, and your alert might fire too frequently. New workloads might require setting

Anomaly detection using dynamic thresholds and two-year-long alerts in Cloud Monitoring Read More »

Modernizing financial services with deployment freedom and transformational AI with AlloyDB Omni

The financial services industry (FSI) operates under a unique set of non-negotiable requirements: the need for strict regulatory compliance, sub-millisecond transactional speeds, and security that verges on impenetrable. Historically, organizations have met these standards by relying on brittle, proprietary database systems, leaving them with massive technical debt, operational overhead, and vendor lock-in. At the same

Modernizing financial services with deployment freedom and transformational AI with AlloyDB Omni Read More »

How Schrödinger sped up molecular discovery by 4x with Alphaevolve

Computational chemistry researchers have traditionally faced a frustrating trade-off when simulating molecular interactions: use fast classical force fields that sacrifice precision or rely on accurate quantum-mechanical methods that run too slowly on large jobs.  Machine-learned force fields (MLFFs) close that gap by training neural networks on high-fidelity quantum data. When it comes to modern drug

How Schrödinger sped up molecular discovery by 4x with Alphaevolve Read More »

Bringing speed and strong cost performance to the market with Gemini Omni Flash and Nano Banana 2 Lite

Great creative happens when your tools move at the speed of your ideas. To help you create rich, reliable experiences while reducing regeneration time and costs, we’re adding two new models to Gemini Enterprise Agent Platform.  First, we’re announcing the general availability of Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image). This model is the

Bringing speed and strong cost performance to the market with Gemini Omni Flash and Nano Banana 2 Lite Read More »

Build agents even faster with Gemini Enterprise Agent Platform’s fully-managed, remote MCP server

A couple of months ago, we announced that over 50 Google-managed MCP servers are available.  Today, we’ll dive into how to use the Gemini Enterprise Agent Platform remote MCP server to securely connect your external AI agents to the resources inside your Google Cloud environment. Connect your IDE to Google Cloud Think of the Agent

Build agents even faster with Gemini Enterprise Agent Platform’s fully-managed, remote MCP server Read More »

Why intent prediction needs more than an LLM​​​​‌‍​‍​‍‌‍‌​‍‌‍‍‌‌‍‌‌‍‍‌‌‍‍​‍​‍​‍‍​‍​‍‌​‌‍​‌‌‍‍‌‍‍‌‌‌​‌‍‌​‍‍‌‍‍‌‌‍​‍​‍​‍​​‍​‍‌‍‍​‌​‍‌‍‌‌‌‍‌‍​‍​‍​‍‍​‍​‍‌‍‍​‌‌​‌‌​‌​​‌​​‍‍​‍​‍‌‍​‌‍‌‌​​‍‍‌​‌‌​‌‍​‌‌‍​‌‍‍‌‍‌‌‍‌‍‌‌‌​‍‌‍‌‍‌‍​‌‍‌‌​‍‍‌‍​‌‍​‍‌‍‍‌‌‍‍‌‌​‌‍‌‌‌‍‍‌‌​​‍‌‍‌‌‌‍‌​‌‍‍‌‌‌​​‍‌‍‌‌‍‌‍‌​‌‍‌‌​‌‌​​‌​‍‌‍‌‌‌​‌‍‌‌‌‍‍‌‌​‌‍​‌‌‌​‌‍‍‌‌‍‌‍‍​‍‌‍‍‌‌‍‌​​‌​‌‌​​​‌‍‌‍​‌​​‌‌​​​​‍‌‌‍​​‍‌​‌​‌‍‌‍​‌‌​‌‌​‍‌​‌​‌‍‌‍​​‌​​‌​‍‌​‍​‌‍​‌‌‍‌​‌‍​​‍‌​‌‌​‌‌​‌‌​‌‍‌‍‌‌​‍​​​‍​​‌‌‍‌‌‌‍​‌​‌​‌​‍‌‌​‌‍‌‌​​‌‍‌‌​‌‌‍​‍‌‍​‌‍‌‍‌‌‌​​‌‍‌​‌‌​​‍‌​​‌‍​‌‌‌​‌‍‍​​‌‌‌​‌‍‍‌‌‌​‌‍​‌‍‌‌​‌‍​‍‌‍​‌‌​‌‍‌‌‌‌‌‌‌​‍‌‍​​‌‌‍‍​‌‌​‌‌​‌​​‌​​‍‌‌​​‌​​‌​‍‌‌​​‍‌​‌‍​‍‌‌​​‍‌​‌‍‌‍​‌‍‌‌​​‍‍‌​‌‌​‌‍​‌‌‍​‌‍‍‌‍‌‌‍‌‍‌‌‌​‍‌‍‌‍‌‍​‌‍‌‌​‍‍‌‍​‌‍​‍‌‍‌‍‍‌‌‍‌​​‌​‌‌​​​‌‍‌‍​‌​​‌‌​​​​‍‌‌‍​​‍‌​‌​‌‍‌‍​‌‌​‌‌​‍‌​‌​‌‍‌‍​​‌​​‌​‍‌​‍​‌‍​‌‌‍‌​‌‍​​‍‌​‌‌​‌‌​‌‌​‌‍‌‍‌‌​‍​​​‍​​‌‌‍‌‌‌‍​‌​‌​‌​‍‌‍‌‌​‌‍‌‌​​‌‍‌‌​‌‌‍​‍‌‍​‌‍‌‍‌‌‌​​‌‍‌​‌‌​​‍‌‍‌​​‌‍​‌‌‌​‌‍‍​​‌‌‌​‌‍‍‌‌‌​‌‍​‌‍‌‌​‍‌‍‌​​‌‍‌‌‌​‍‌​‌​​‌‍‌‌‌‍​‌‌​‌‍‍‌‌‌‍‌‍‌‌​‌‌​​‌‌‌‌‍​‍‌‍​‌‍‍‌‌​‌‍‍​‌‍‌‌‌‍‌​​‍​‍‌‌

Ryan sits down with Frank Portman, CTO at Yobi, to talk about why next-token prediction, though great for language, isn’t the right inductive bias for forecasting human behavior. They discuss how Yobi builds a “foundation model of behavior” using transformers and graph neural networks instead of chat-style LLMs, and what it takes to run millions

Why intent prediction needs more than an LLM​​​​‌‍​‍​‍‌‍‌​‍‌‍‍‌‌‍‌‌‍‍‌‌‍‍​‍​‍​‍‍​‍​‍‌​‌‍​‌‌‍‍‌‍‍‌‌‌​‌‍‌​‍‍‌‍‍‌‌‍​‍​‍​‍​​‍​‍‌‍‍​‌​‍‌‍‌‌‌‍‌‍​‍​‍​‍‍​‍​‍‌‍‍​‌‌​‌‌​‌​​‌​​‍‍​‍​‍‌‍​‌‍‌‌​​‍‍‌​‌‌​‌‍​‌‌‍​‌‍‍‌‍‌‌‍‌‍‌‌‌​‍‌‍‌‍‌‍​‌‍‌‌​‍‍‌‍​‌‍​‍‌‍‍‌‌‍‍‌‌​‌‍‌‌‌‍‍‌‌​​‍‌‍‌‌‌‍‌​‌‍‍‌‌‌​​‍‌‍‌‌‍‌‍‌​‌‍‌‌​‌‌​​‌​‍‌‍‌‌‌​‌‍‌‌‌‍‍‌‌​‌‍​‌‌‌​‌‍‍‌‌‍‌‍‍​‍‌‍‍‌‌‍‌​​‌​‌‌​​​‌‍‌‍​‌​​‌‌​​​​‍‌‌‍​​‍‌​‌​‌‍‌‍​‌‌​‌‌​‍‌​‌​‌‍‌‍​​‌​​‌​‍‌​‍​‌‍​‌‌‍‌​‌‍​​‍‌​‌‌​‌‌​‌‌​‌‍‌‍‌‌​‍​​​‍​​‌‌‍‌‌‌‍​‌​‌​‌​‍‌‌​‌‍‌‌​​‌‍‌‌​‌‌‍​‍‌‍​‌‍‌‍‌‌‌​​‌‍‌​‌‌​​‍‌​​‌‍​‌‌‌​‌‍‍​​‌‌‌​‌‍‍‌‌‌​‌‍​‌‍‌‌​‌‍​‍‌‍​‌‌​‌‍‌‌‌‌‌‌‌​‍‌‍​​‌‌‍‍​‌‌​‌‌​‌​​‌​​‍‌‌​​‌​​‌​‍‌‌​​‍‌​‌‍​‍‌‌​​‍‌​‌‍‌‍​‌‍‌‌​​‍‍‌​‌‌​‌‍​‌‌‍​‌‍‍‌‍‌‌‍‌‍‌‌‌​‍‌‍‌‍‌‍​‌‍‌‌​‍‍‌‍​‌‍​‍‌‍‌‍‍‌‌‍‌​​‌​‌‌​​​‌‍‌‍​‌​​‌‌​​​​‍‌‌‍​​‍‌​‌​‌‍‌‍​‌‌​‌‌​‍‌​‌​‌‍‌‍​​‌​​‌​‍‌​‍​‌‍​‌‌‍‌​‌‍​​‍‌​‌‌​‌‌​‌‌​‌‍‌‍‌‌​‍​​​‍​​‌‌‍‌‌‌‍​‌​‌​‌​‍‌‍‌‌​‌‍‌‌​​‌‍‌‌​‌‌‍​‍‌‍​‌‍‌‍‌‌‌​​‌‍‌​‌‌​​‍‌‍‌​​‌‍​‌‌‌​‌‍‍​​‌‌‌​‌‍‍‌‌‌​‌‍​‌‍‌‌​‍‌‍‌​​‌‍‌‌‌​‍‌​‌​​‌‍‌‌‌‍​‌‌​‌‍‍‌‌‌‍‌‍‌‌​‌‌​​‌‌‌‌‍​‍‌‍​‌‍‍‌‌​‌‍‍​‌‍‌‌‌‍‌​​‍​‍‌‌ Read More »

Supercharging the agentic era with Spanner’s multi-model architecture

In the agentic era, the role of the database has fundamentally changed. It is no longer a passive repository; it’s a critical context engine designed to ground generative AI apps, models and power autonomous workflows. To do this effectively, databases must move beyond fragmented architectures and embrace a unified, multi-model foundation, facilitating deep reasoning and

Supercharging the agentic era with Spanner’s multi-model architecture Read More »

Lessons learned from scaling to 1 million Lambda functions

In this post, we share our journey and the lessons learned from building and running a fully serverless, multi-account software as a service (SaaS) platform at scale. We’ll explore why true scale-to-zero is critical, how we handle quota management, why engaging AWS service teams early saved us from outages, and which unexpected practices emerged once

Lessons learned from scaling to 1 million Lambda functions Read More »