Docs

TandemLLM

TandemLLM's docs live in the repository, next to the code they describe.

The docs folder

Setup, the chat, exactness, how things are measured, and a page per model and weight pack.

github.com/0xBakeer/TandemLLM

The manual

The whole engine in one PDF, from the path of a request down to the kernels.

PDF, in the repository

Changelog

Every release, what changed in it, and the run that showed it.

CHANGELOG.md

Inference Atlas

A public atlas of measured inference setups. Engine, version, quantization, flags and workload together decide a number, so each measurement is one JSON file that records all of them, and the repository is the database.

Rendered from github.com/0xBakeer/inference-atlas