# SGLang explains how it matched DeepInfer on prefill and decode

> Original title: Lots of you have been wondering how SGLang matched DeepInfer.

- Source: SGLang
- Published: 2026-10-27T21:01:56.000Z
- Bad Influence: https://badinfluence.news/items/fetk2e72bxekzg2nxxn2xzy0i
- Original: https://x.com/sgl_project/status/2115187263315591550

## Summary

SGLang's account of matching DeepInfer's throughput is out as a two-minute explainer covering the benchmarks and the DeepSeek kernels now in SGLang. Its earlier post reports up to 1.04× prefill throughput on 4× GB300 and 4× B300, and up to 7.4% decode throughput on 64× GB300. The post also links to an end-to-end reproduction guide.

## Post

Lots of you have been wondering how SGLang matched DeepInfer. 

So we made a 2-minute explainer: the benchmarks, the DeepSeek kernels now in SGLang, and how you can reproduce the results. Check it out! 👇

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2115176585917874176%2Fimg%2FQNY_8nTvvoNdyUFZ.jpg&mode=thumb&exp=1793404800&sig=b3597db48cc5f885)

## Quoted post @sgl_project

> DeepInfer set the bar. SGLang pushed it higher! 🚀
> 
> SGLang now matches DeepInfer performance on BOTH prefill and decode:
> 
> • Prefill: Up to 1.04× throughput on 4× GB300 and 4× B300
> • Decode: Up to 7.4% throughput on 64× GB300
> 
> We also provide an end-to-end reproduction guide and a full serving stack to run it in production.

https://x.com/sgl_project/status/2114071115605877043