# NVIDIA engineers explain tuning SGLang for Vera Rubin and large MoE models

> Original title: @nvidia's Lee Nau and Akhil Goel share what it took to bring SGLang to Vera Rubin, find performance bottlenecks, and tune kernels and att...

- Source: SGLang
- Published: 2026-11-07T00:28:49.000Z
- Bad Influence: https://badinfluence.news/items/wuc4tcp2eos4ywzzsoogfxunn
- Original: https://x.com/sgl_project/status/2118863204805902589

## Summary

NVIDIA engineers Lee Nau and Akhil Goel describe what it took to bring SGLang to Vera Rubin. They cover finding performance bottlenecks and tuning kernels and attention for large MoE models.

## Post

@nvidia's Lee Nau and Akhil Goel share what it took to bring SGLang to Vera Rubin, find performance bottlenecks, and tune kernels and attention for large MoE models.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWeyDJLaIAA0Hz3.jpg&mode=thumb&exp=1794268800&sig=5925f68042fe57de)