Machine Learning

AI in its Native Habitat: WebLLM, WebSD, and MLC-LLM

The future is hybrid edge-cloud AI

What the $28 million Series B means for OctoML and for accelerating ML deployment?

I’m thrilled to announce that OctoML has closed a $28M million Series B funding round led by Addition and Lee Fixel with…

Auto-scheduling now available in TVM

Supporting broader model and hardware coverage, and even easier custom op support.

Up to 9x performance improvements with TVM’s new auto-scheduler

Compiling classical ML for (up to 30x) performance gains and hardware portability

OctoML and Microsoft make classical machine learning even faster.

Octomizer Early Access Is Here!

We’re excited to announce that the Octomizer is now open for Early Access!

This post now lives at: https://octoml.ai/blog/octoml-early-access-is-here/

Using Sparsity in Apache TVM to halve your cloud bill for NLP

By Joshua Fromm, Bing Xu, Morgan Funtowicz and Jason Knight

Leveraging block sparsity with Apache TVM to halve your cloud bill for NLP

TinyML: TVM taming the final (ML) frontier

Machine learning on embedded platforms

Authors: Logan Weber and Andrew Reusch

This post now lives at: https://octoml.ai/blog/tinyml-tvm-taming-the-final-ml-frontier