Cover Image for MLn Club (ML Reading Group) #4: Touching The Elephant - TPUs

Presented by

We meet weekly on Mondays in person to talk about new ML papers! As always, optional quiet reading from 7 pm, discussion starts 8 pm. Come and join the discussion! Website: https://czhs.github.io/mln/

Hosted By

13 Went

AI

MLn Club (ML Reading Group) #4: Touching The Elephant - TPUs

Name: MLn Club (ML Reading Group) #4: Touching The Elephant - TPUs
Start: 2026-06-08T19:00:00.000-04:00
End: 2026-06-08T21:00:00.000-04:00
Location: Pittsburgh, PA

MLn Reading Club

Register to See Address

Pittsburgh, PA

Past Event

Welcome! To join the event, please register below.

About Event

Week 4: Tensor Processing Units

What if the real moat in AI isn't the model, but the chip?

Should AI run on custom silicon or general-purpose chips?

Touching the Elephant Reed Oliver
This article is a deep dive into the history and architecture of Google's Tensor Processing Units (TPUs) — custom silicon that now powers the world's most advanced AI models. Reed Oliver traces how Google moved away from general-purpose chips to build dedicated, "monastic" hardware optimised for one thing: matrix multiplication at scale.
The piece explores why Google made the bet on custom hardware when GPUs were already dominant, what makes TPUs architecturally different, and how that decision reshaped the broader AI industry — from training costs to the competitive landscape.

Join us at CASI for discussion at 8 pm, (optional) quiet reading from 7 pm.

Reading Recommendations, Questions, or Comments? Contact us here!

Location

Please register to see the exact location of this event.