Powering cost-efficient AI inference at scale with Cloud TPU v5e on GKE (cloud.google.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of cloud.google.com: Powering cost-efficient AI inference at scale with Cloud TPU v5e on GKE

First screen, captured 2 years ago.

Looks similar

Screenshot of cloud.google.com: TPU v4 provides exaFLOPS-scale ML with efficiency gains

TPU v4 provides exaFLOPS-scale ML with efficiency gains (cloud.google.com)

95 points by zekrioca 3 years ago | 33 comments

Screenshot of cloud.google.com: Cloud TPU v5p and AI Hypercomputer

Cloud TPU v5p and AI Hypercomputer (cloud.google.com)

154 points by treesciencebot 2 years ago | 62 comments

Screenshot of cloud.google.com: Building the largest known Kubernetes cluster

Building the largest known Kubernetes cluster (cloud.google.com)

144 points by TangerineDream 11 months ago | 80 comments

Screenshot of cloud.google.com: Google Cloud TPU Multislice Training

Google Cloud TPU Multislice Training (cloud.google.com)

102 points by infixed 3 years ago | 43 comments

Screenshot of cloud.google.com: TPU transformation: A look back at 10 years of our AI-specialized chips

TPU transformation: A look back at 10 years of our AI-specialized chips (cloud.google.com)

116 points by mariuz 2 years ago | 44 comments

Screenshot of cloud.google.com: Colossus for Rapid Storage

Colossus for Rapid Storage (cloud.google.com)

226 points by alobrah 1 year ago | 103 comments