All Posts

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

Wildlife Studios’s ML team was deploying sets of ensemble models using Flask. It quickly became too hard and too expensive to scale. By using Ray Serve, Wildlife Studios was able to improve the latency and throughput while reducing the cost. Ray Serv...

DendraInferencePipeline
10 . 12 . 2021

How Ray and Anyscale make it easy to do massive-scale machine learning on aerial imagery

Dendra Systems’ mission is to enable faster, high-quality, transparent and scalable restoration. They do this using a variety of tools like drones for ultra-high resolution mapping at an unprecedented scale, machine learning algorithms that analyze i...

Ray 1.7
10 . 11 . 2021

Ray version 1.7 has been released

Ray version 1.7 is here. Highlights include: Ray SGD v2 and is in alpha, Ray Workflows is in alpha, and major enhancements to the C++ API

mlplatformCropped
10 . 06 . 2021

Why Third Generation ML Platforms are More Performant

In a previous blog post, we defined a "3rd generation ML platform" as one that offered full programmability for ML workflows. Key to a 3rd generation platform is the concept of a programmable compute layer. In this blog, we report on emerging pattern...

Where Ray Serve Fits In
10 . 01 . 2021

Serving ML Models in Production: Common Patterns

Over the past couple years, we've listened to ML practitioners across many different industries to learn and improve the tooling around ML production use cases. Through this, we've seen 4 common patterns of machine learning in production: pipeline, e...

Wildlife Studios
09 . 23 . 2021

Wildlife Studios serves in-game offers 3X faster with Ray Serve

Mobile gaming giant Wildlife Studios’ legacy system for serving revenue-generating in-game offers was not scaling to meet their latency and cost requirements. After switching to Ray Serve on Anyscale, their Dynamic Offers team is now able to serve of...

Uber Leveraging Ray
09 . 15 . 2021

The Third Generation of Production ML Architectures

As technology has advanced, production ML architectures have evolved. One way to see it is in terms of generations: The first generation involved “fixed function” pipelines, while the second generation involved programmability within the pipeline of...

Ant Ray Serving Architecture
09 . 08 . 2021

Building Highly Available and Scalable Online Applications on Ray at Ant Group

Ant Group has developed Ant Ray Serving which is an online service framework based on Ray, which provides users with a Serverless platform to publish Java/Python code as online services. The platform provides users with basic capabilities such as dep...

With and without NumPy Ray
09 . 02 . 2021

Parallelizing Python Code

This article reviews some common options for parallelizing Python code including process-based parallelism, specialized libraries, ipython parallel, and Ray.

ML Platform
08 . 31 . 2021

How Anastasia accelerated their ML processes 9x with Ray and Anyscale

Anastasia.ai provides a powerful platform that enables organizations to operate AI capacities at scale with a fraction of the resources and effort traditionally required. This post covers a demand prediction problem we had and how using Ray to solve...