Read the launch

about

A small lab for shared inference.

{/* Manifesto with founder names hidden for now — re-enable the named version by reverting to the previous commit, or keeping this file commented and adding it back when names are public. */}

Coconut Labs is a small inference research lab. We work on schedulers, systems notes, and the small pieces of infrastructure that decide whether shared compute behaves like a tool or a tax.

The lab is intentionally small: two engineers, close to the measurements. A result should have a harness. A claim should have a number. A page should leave enough quiet around the thing it is trying to say.

The first public thread is KVWarden: tenant fairness on shared inference. mlxd follows the same line closer to local Apple Silicon inference. Both projects are about making the shared layer more honest under pressure.

How we work

Honest scale

Coconut Labs is Shrey Patel and Jay Patel. Two people, close to the work, no fake-team plurals beyond that.

Specific numbers

A result earns attention when the units are visible. Latency, pressure, and failure modes stay in frame.

Boring infrastructure

Schedulers, harnesses, and traces are not decoration. They are the artifact.

Ship the code first

A post can be elegant. The repository still has to run.

Slow web

Pages should feel like edited pages. Motion is allowed when it carries meaning.