---
type: "Topics"
locale: "en"
url: "https://longbridge.com/en/topics/100000000879338.md"
description: "NVIDIA LPU supports 3 types of disaggregated inferencing:1. Rubin Prefill + LPU Decode for the fastest interactivity2. Rubin Prefill + Rubin Decode Attention + LPU Decode FFN for the middle of the curve3. Rubin Prefill + Rubin Decode Verification + LPU Drafter for the middle-left of the curveFor low interactivity, raw Rubin still takes the win. Looking forward to seeing Rubin + LPU performance curves on open-source agentic benchmarks like AgentX."
datetime: "2026-08-31T17:06:48.000Z"
locales:
  - [en](https://longbridge.com/en/topics/100000000879338.md)
  - [zh-CN](https://longbridge.com/zh-CN/topics/100000000879338.md)
  - [zh-HK](https://longbridge.com/zh-HK/topics/100000000879338.md)
author: "[@SemiAnalysis](https://longbridge.com/en/profiles/2078041753485574144.md)"
generator: "portal-rs"
---

# NVIDIA LPU supports 3 types of disaggregated infer…


### Related Stocks

- [NVDA.US](https://longbridge.com/en/quote/NVDA.US.md)
- [NVD.DE](https://longbridge.com/en/quote/NVD.DE.md)

---
> **Disclaimer: This article is for reference only and does not constitute any investment advice.**