Featured Posts and News

Ray Summit 2025: Call for Proposals Closes on June 30th, 2025
05 . 30 . 2025

Ray Summit 2025: Call for Proposals Closes on June 30th, 2025

04 . 09 . 2025

Simplifying AI Development at Scale: Google Cloud Integrates Anyscale's RayTurbo with GKE

10 . 03 . 2024

Ray Summit 2024: Breaking Through the AI Complexity Wall

image4

10 . 01 . 2024

Autoscaling Large AI Models up to 5.1x Faster on Anyscale

By Christopher Chou, 
Austin Kuo, 
Richard Liaw, 
Edward Oakes and 
Chris Sivanich
ray-serve-ga-blog

09 . 25 . 2023

Ray Serve: Tackling the cost and complexity of serving AI in production

By Akshay Malik, 
Edward Oakes and 
Phi Nguyen
ray-serve-ga-blog

09 . 25 . 2023

Ray Serve: Tackling the cost and complexity of serving AI in production

By Akshay Malik, 
Edward Oakes and 
Phi Nguyen
ray-serve-ga-blog

09 . 25 . 2023

Ray Serve: Tackling the cost and complexity of serving AI in production

By Akshay Malik, 
Edward Oakes and 
Phi Nguyen
blog-deployment-graph-api-thumb

05 . 18 . 2022

Multi-model composition with Ray Serve deployment graphs

By Jiao Dong, 
Shreyas Krishnaswamy, 
Simon Mo and 
Edward Oakes
blog-runtime-env-thumb

05 . 05 . 2022

Handling files and packages on your cluster with Ray runtime environments

By Archit Kulkarni and 
Edward Oakes
The live traffic pattern is variable and predictable. Serve’s replica autoscaling drives the cost down further during idle time.

10 . 19 . 2021

Cheaper and 3X Faster Parallel Model Inference with Ray Serve

By Leonnardo Rabello, 
Lucas Machado, 
Simon Mo and 
Edward Oakes
Where Ray Serve Fits In

10 . 01 . 2021

Serving ML Models in Production: Common Patterns

By Simon Mo, 
Edward Oakes and 
Michael Galarnyk