Cost-efficient AI inference
Learn how to use JAX, Google Kubernetes Engine (GKE) and NVIDIA Triton Inference Server as a winning combination for low cost AI inference.
Speaker: Don McCasland
Products Mentioned: AI Infrastructure
Google Cloud Tech
Helping you build what's next with secure infrastructure, developer tools, APIs, data analytics and machine learning....

Build AI Agents on GKE in the GKE Turns 10 Hackathon

Google Cloud Tech

Visualizing BigQuery geospatial data in Colab

Google Cloud Tech

How to deploy a container image to Cloud Run

Google Cloud Tech

The Agent Factory - Episode 4: Remember me: Memory in Agents

Google Cloud Tech

Container-Optimized Compute Platform for GKE Autopilot

Google Cloud Tech

The Future of Automation: How AI Agents are Revolutionizing Data and Robotics

Google Cloud Tech

Enable Looker Studio report generation with one click!

Google Cloud Tech

GKE Inference Reference Architecture, Your Blueprint for Production-Ready Inference

Google Cloud Tech

This Month in GKE: July Edition

Google Cloud Tech

The Agent Factory - Episode 3: Building Custom Tools for Agents

Google Cloud Tech

The future of AI architecture: Using agents to supervise other agents

Google Cloud Tech

What is Private Google Access?

Google Cloud Tech

Defining AI agents: From definitions to stopping conditions

Google Cloud Tech

The AI Agent Bake-Off Ep.1 Trailer / Can They Build an AI Agent in 3 Hours?

Google Cloud Tech

The AI Agent Bake-Off Ep.1 | Can they build an AI Agent in 3 hours?

Google Cloud Tech

Roll & Score: Evolve arcade with AI

Google Cloud Tech

How to use Agentspace search on Google Distributed Cloud

Google Cloud Tech

AI Agents: From concept to code

Google Cloud Tech

Let’s build a GenAI app on Cloud Run

Google Cloud Tech

Save time and follow data best practices with Looker Blocks!

Google Cloud Tech

Unlock AI Potential: Introducing the Google Cloud & NVIDIA Community

Google Cloud Tech

Self Serving Allowlisting of Privileged Apps on GKE Autopilot

Google Cloud Tech

The Agent Factory - Episode 2: Multi-Agent Systems, Concepts & Patterns

Google Cloud Tech

Develop with Looker and Looker Studio

Google Cloud Tech

Is your Infrastructure Ready for GPUs and AI Agents?

Google Cloud Tech

Build AI agents with Cloud Run and Firebase Genkit

Google Cloud Tech

The Agent Factory - Episode 1: Agents, their frameworks and when to use them

Google Cloud Tech

Agentic Business Intelligence done right

Google Cloud Tech

Ways to enhance your developers’ productivity with Gemini

Google Cloud Tech

Platform engineering: building a developer platform

Google Cloud Tech

Develop with Looker Studio Community Connectors and Visualizations

Google Cloud Tech

How to Turn Images Into Animated Stories Using Gemini and Veo 2

Google Cloud Tech

Secure Your AI Lifecycle with AI Protection in Security Command Center

Google Cloud Tech

Build AI Agents in the Agent Development Kit Hackathon

Google Cloud Tech

This Month in GKE: April Edition

Google Cloud Tech

Ground Gemini with Google Search with the Gen AI SDK

Google Cloud Tech

Effortless Image Editing + Animation with Gemini 2.0 Flash and Veo 2

Google Cloud Tech

Scaling your tuned models with Cloud Run

Google Cloud Tech

Optimizing AI infrastructure for modern retail

Google Cloud Tech

Watch devs analyze Formula E races with Google Cloud

Google Cloud Tech

Sentiment analysis with LLMs/BQML over your data

Google Cloud Tech

How to optimize costs and fuel innovation by moving VMware to Google Cloud

Google Cloud Tech

How Google Cloud makes AI scale at unbelievable speed!

Google Cloud Tech

AI Crash Course: From Still to Motion: Create Visuals & Videos with Imagen 3 and Veo 2

Google Cloud Tech

Evaluating and Debugging Non-Deterministic AI Agents

Google Cloud Tech

What is Gemini in BigQuery?

Google Cloud Tech

How to host DeepSeek with Cloud Run GPUs in 3 steps

Google Cloud Tech

Memory in AI agents

Google Cloud Tech

Supercharge your AI/ML: Designing effective GCP storage

Google Cloud Tech

Build an app by just talking about it with Gemini!

Google Cloud Tech

Watch Gemini judge the Quick Build game show!

Google Cloud Tech

Why use GKE to deploy models?

Google Cloud Tech

Platform engineering with Cloud Run

Google Cloud Tech

Conversational vs non-conversational AI agents

Google Cloud Tech

Build a better AI model by fine tuning Gemini

Google Cloud Tech

Fine tuning Gemini with Google AI Studio

Google Cloud Tech

How Gemini helps predict wildfire behavior

Google Cloud Tech

How a cloud architect predicts wildfire behavior with Google Cloud

Google Cloud Tech

How a startup founder uses Google Cloud to predict wildfire behavior

Google Cloud Tech

How a software engineer predicts wildfire behavior with Google Cloud

Google Cloud Tech

Cloud Load Balancer, the secret to uptime for AI inference

Google Cloud Tech

The secret to AI training at Google scale

Google Cloud Tech

Develop with AI Hypercomputer

Google Cloud Tech

Cost-efficient AI inference

Google Cloud Tech

Cluster toolkit: The secret to making AI setup easy

Google Cloud Tech

Hypercomputer Clusters: The secret to AI training at Google scale

Google Cloud Tech

The secret to cost-efficient AI inference

Google Cloud Tech

How Improving Aviation uses Gemini and Google Cloud to predict and combat wildfires

Google Cloud Tech

Understanding and unifying Looker and Looker Studio

Google Cloud Tech

Agentic AI: Workflows vs. agents

Google Cloud Tech

Fine-tuning use cases

Google Cloud Tech

Connect your language model with external systems and APIs

Google Cloud Tech

Function calling with the Gemini API

Google Cloud Tech

Looker Reports: an end-to-end demo

Google Cloud Tech

Gemini 2.0 and the Gen AI SDK: A powerful duo

Google Cloud Tech

Kubernetes jobs for batch workload

Google Cloud Tech

Austin & Seattle- rsvp for our in-person events!

Google Cloud Tech

Level up your Google Colab notebooks

Google Cloud Tech

How to use widgets and forms in Google Colab

Google Cloud Tech

Build compelling data stories with Looker reports

Google Cloud Tech

Develop with Looker Extensions

Google Cloud Tech

Batch architecture in Kubernetes

Google Cloud Tech

Take your AI projects further with Google AI Studio

Google Cloud Tech

Google AI Studio: Advanced features

Google Cloud Tech

Develop with Looker Embedding

Google Cloud Tech

Grounding with Google Search: Build reliable AI with Google AI Studio

Google Cloud Tech

Streamline calculated fields with Gemini’s formula assistant

Google Cloud Tech

How to develop with Looker Blocks

Google Cloud Tech

? Problem: Too much data for embedding? ?? Solution: Chunk your data! ✂️

Google Cloud Tech

What is HPC and HTC?

Google Cloud Tech

Intro to developing with Looker and Looker Studio

Google Cloud Tech

Boost Keras performance with multi-backend and JAX

Google Cloud Tech

How to migrate your Keras code to JAX

Google Cloud Tech

No-Fuss AI Database Connections with GenAI Toolbox

Google Cloud Tech

What is NotebookLM?

Google Cloud Tech

Create a Artifact Registry Docker repository on Google Cloud

Google Cloud Tech

Intro to multimodal RAG systems

Google Cloud Tech

Why should developers use Google AI Studio?

Google Cloud Tech

Google AI Studio: Your AI playground ??

Google Cloud Tech

Google AI Studio for Beginners

Google Cloud Tech