# SGLang matches DeepInfer on prefill and decode throughput

> Original title: DeepInfer set the bar. SGLang pushed it higher! 🚀

- Source: SGLang
- Published: 2026-10-24T19:06:46.000Z
- Bad Influence: https://badinfluence.news/items/aal2pb4xnhhk5ytj5v2g3kjsa
- Original: https://x.com/sgl_project/status/2114071115605877043

## Summary

SGLang says it now matches DeepInfer performance on both prefill and decode. It reports up to 1.04× prefill throughput on 4× GB300 and 4× B300, and up to 7.4% decode throughput on 64× GB300. The project also provides an end-to-end reproduction guide and a full serving stack for production use.

## Post

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://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVav3WybEAE915U.jpg&mode=thumb&exp=1793404800&sig=6a19b4933a0c1494)