TensorFlow Serving 1.0
We've come a long way since our initial open source release in February 2016 of TensorFlow Serving, a high performance serving system for machine learned models, designed for production environments. Today, we are happy to announce the release of TensorFlow Serving 1.0. Version 1.0 is built from TensorFlow head, and our future versions will be minor-version aligned with TensorFlow releases.
Smaller Fonts with WOFF 2.0 and unicode-rangedevelopers.googleblog.com
1,000 Chrome Experiments and counting...developers.googleblog.com
Introducing gRPC, a new open source HTTP/2 RPC Frameworkdevelopers.googleblog.com
Reminder to migrate to OAuth 2.0 or OpenID Connectdevelopers.googleblog.com
LiteRT.js, Google's high performance Web AI Inferencedevelopers.googleblog.com
Reminder: ClientLogin Shutdown scheduled for April 20, 2015developers.googleblog.com
Grafana Is Not Worried About AWS CommercializationThenewstack
How to serve trillions of tokens for trillion-parameter coding agentsModal
Modal Clusters are generally availableModal
Modernizing marketing at a 56-year-old nonprofit | ZapierZapier
How Orange uses AI video to rapidly upskill their internal teamsSynthesia
Accelerating ML with TensorFlow.js: Using Pretrained Models and DockerDocker
How Notion helped a college “tools guy” build a business serving 150+ clientsNotion So
Get started with the latest updates for Dockerfile syntax (v1.7.0)Docker
Securing GitHub Actions CI dependencies: Recipe cardCncf
Improving Composer through real-time RL · CursorCursor
Vision Model Platform Updates: Enhanced Capabilities and New FeaturesFireworks
Kubernetes WG Serving concludes following successful advancement of AI inference supportCncf
Why goodput matters more than throughput for LLM servingCncf
Model Vault: Secure, Scalable Model Inference | CohereCohere
