Author

A. ShahirM

1 paper indexed here

Fetches their full publication history.

Not the right person? Other researchers publish under this name.

#small language model Preprint Aug 2026

What actually runs: a measurement study of language model placement and decode speed on the Apple Neural Engine

This work sweeps a 64-shape matrix of LLM primitives that varies how a computation is expressed while holding what it computes fixed, recording per-operation device support and finds that placement is a property of how a computation is expressed, not of what it computes.

A. ShahirM · 0 citations