The Serving Stack
Start hereCollectionsNewsletter
Sign in

deepgemm

1 post

GPU FOR INFERENCE · 031×128 TILES · 128×128 BLOCKSFP8ONE SCALE PER TILE
gpu-for-inferencedeepgemmgpu

DeepGEMM: The Matrix Multiplications Behind DeepSeek's Models

What DeepGEMM computes for DeepSeek's models: block-scaled FP8 and FP4 matrix multiplications, grouped GEMMs for MoE experts, and the fused Mega MoE kernel.

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.