Spell Blog
Product Updates
Online batching with Spell serving
January 12th, 2021
The new online batching feature we've added to Spell model servers can be used to significantly improve your model runtime performance in production.
MLOps
A deep dive into AWS spot instance interruptions
January 7th, 2021
What 12,000 spot instance runs tell us about spot instance interruptions on AWS
MLOps
An introduction to AutoML with Ludwig
January 5th, 2021
Ludwig is an open-source AutoML tool. In this blog post, we explain how it works.
Product Updates
Accessing GCP services from within Spell using custom instance profiles
December 30th, 2020
A guide to integrating Spell with your existing GCP services
MLOps
A developer-friendly guide to model pruning in PyTorch
December 16th, 2020
Model pruning can substantially speed up model inference time and reduce model size.
Product Updates
Accessing Snowflake with Spell
December 4th, 2020
We break down how to use Snowflake's database connector to access a running Snowflake instance from within Spell.
Ready to Get Started?
Create an account in minutes or connect with our team to learn how Spell can accelerate your business.