---
title: "Discussion on \"RoCE Explained: How RDMA over Ethernet Enables Scalable AI Inference\" | Hashnode"
description: "Discussion on \"RoCE Explained: How RDMA over Ethernet Enables Scalable AI Inference\". Explore RoCE v2 networks with RDMA, lossless Ethernet, RoCE adapters, switches, and InfiniBand comparisons for AI inference, cloud, and HPC scenarios."
url: "https://hashnode.com/posts/roce-explained-how-rdma-over-ethernet-enables-scalable-ai-inference/6a841b702514a98192246b72"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [RoCE Explained: How RDMA over Ethernet Enables Scalable AI Inference](https://aicplight.hashnode.dev/roce-explained-how-rdma-over-ethernet-enables-scalable-ai-inference?utm_source=hashnode&utm_medium=feed)

Explore RoCE v2 networks with RDMA, lossless Ethernet, RoCE adapters, switches, and InfiniBand comparisons for AI inference, cloud, and HPC scenarios.

Aug 18 · 6 min read · aicplight.hashnode.dev  
Read the article

-   [#roce](https://hashnode.com/tag/roce)
-   [#rdma](https://hashnode.com/tag/rdma)
-   [#inference](https://hashnode.com/tag/inference)

## Written by

[Weiwei Zhang](https://hashnode.com/@aicplight)

@aicplight

  
[View profile](https://hashnode.com/@aicplight)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.