The Serving Stack
Start hereCollectionsNewsletter
Sign in

smoothquant

1 post

QUANTIZATION · 07ACTIVATIONS÷ sSMOOTHEDMAX 17.5 → 1.32, PRODUCT UNCHANGED
quantizationsmoothquantfp8

SmoothQuant and W8A8: Quantizing Activations Too

Why activation outliers break INT8, how SmoothQuant moves them into the weights, and what it changes for FP8 W8A8, measured on Qwen3-8B with vLLM.

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.