The Serving Stack
Start hereCollectionsNewsletter
Sign in

hardware

1 post

NUMBER FORMATS · 0816-BIT2.5 PF8-BIT5 PF4-BIT10 PF2×PER HALVINGDENSE TENSOR-CORE RATE, ONE GB200 GPU
formatsgpuhardware

Which GPU Computes Which Format: Ampere to Rubin, MI300 to MI355

Which number formats each data-center GPU computes natively, at what rate, from the vendors' own pages: A100 to Rubin, MI300X to MI355X.

by The Serving Stack

Inference Notes

Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.

The Serving Stack

Inference Engineering, In Depth

Navigate

HomeStart hereCollectionsNewsletterAll articles

Collections

Inference EnginesHow an LLM Request Becomes TokensLLMs, ExplainedThe GPU for Inference EngineersQuantization in PracticeServing in Production

Links

RSS Feed

Legal

Privacy PolicyTerms of ServiceCookie Policy
© 2026 The Serving Stack. All rights reserved.