Co-Founder

Phil Howes

About

Phil Howes is a co-founder of Baseten, where he leads infrastructure. Phil has spent his career solving interesting problems, from his Ph.D. in Mathematics at The University of Sydney to working in ML at startups like Gumroad and Shape Analytics, which he co-founded in 2015 and was acquired in 2019. Outside of work, Phil lives in Oakland, CA with his family and enjoys woodworking, guitar, and running.

Model performance

How multi-node inference works for massive LLMs like DeepSeek-R1

Running DeepSeek-R1 on H100 GPUs requires multi-node inference to connect the 16 H100s needed to hold the model weights.

1 other
News

Introducing Baseten Hybrid: control and flexibility in your cloud and ours

Baseten Hybrid is a multi-cloud solution that enables you to run inference in your cloud—with optional spillover into ours.

2 others
Glossary

The benefits of globally distributed infrastructure for model serving

Multi-cloud and multi-region infrastructure for model serving provides availability, redundancy, lower latency, cost savings, and data residency compliance.

1 other
Hacks & projects

Serving four million Riffusion requests in two days

Riffusion is a fine-tuned version of Stable Diffusion. Baseten served Riffusion over four million times in a couple of days, serving top-of-hacker-news traffic.

Product

Why we built and open-sourced a model serving solution

Truss, our open-sourced bridge for model development to deployment, saves time for data scientists and ML engineers on MLOps tasks in model serving.

Machine learning infrastructure that just works

Baseten provides all the infrastructure you need to deploy and serve ML models performantly, scalable, and cost-efficiently.