# SGLang doubles DeepSeek V4.1 Flash low-latency and throughput speeds

> Original title: We’ve been working to push both ends of the curve on DeepSeek V4.1 Flash 🚀

- Source: SGLang
- Published: 2026-10-26T22:27:43.000Z
- Bad Influence: https://badinfluence.news/items/mtnre0aeopdcr5b27tz2i2kyp
- Original: https://x.com/sgl_project/status/2114846465399144694

## Summary

SGLang says its MegaKernel optimizations raise DeepSeek V4.1 Flash interactivity from 538 to 943 tokens per second per user. Its WideEP and system-wide optimizations raise total throughput from 348K to 654K tokens per second per GPU, counting cache, new input, and output tokens. The project says further improvements are still possible and promises more updates soon.

## Post

We’ve been working to push both ends of the curve on DeepSeek V4.1 Flash 🚀

• For low latency, our MegaKernel optimizations take interactivity from 538 to 943 tok/s/user. 
• For high throughput, WideEP and system-wide optimizations take total throughput (cache + new input + output) from 348K to 654K tok/s per GPU.  

There’s still lots of room for improvement. We’ll share more updates soon.

## Quoted post @SemiAnalysis_

> Congrats to the SGLang and RadixArk team for their amazing work on MegaKernel + PD, improving both high concurrency throughput and low-latency serving as well! (1/2)🧵

https://x.com/SemiAnalysis_/status/2114779348838338719