---
title: "Discussion on \"LLM-D: Serving AI Inference at scale\" | Hashnode"
description: "Discussion on \"LLM-D: Serving AI Inference at scale\". Introduction:\n\nAI inference is the \"doing\" part of artificial intelligence. It's the moment a trained model stops learning and starts working, turning its knowledge into real-world results.\n\nWe all use cutting-edge frontier models in our day-to-day u..."
url: "https://hashnode.com/posts/llm-d-serving-ai-inference-at-scale/695b56c916750a1492eb6bd4"
---

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

Discussion

# [LLM-D: Serving AI Inference at scale](https://srujanpakanati.com/llm-d-serving-ai-inference-at-scale?utm_source=hashnode&utm_medium=feed)

Introduction: AI inference is the "doing" part of artificial intelligence. It's the moment a trained model stops learning and starts working, turning its knowledge into real-world results. We all use cutting-edge frontier models in our day-to-day u...

Jan 5 · 3 min read · srujanpakanati.com  
Read the article

-   [#llm-d](https://hashnode.com/tag/llm-d)
-   [#kubernetes-for-ai](https://hashnode.com/tag/kubernetes-for-ai)
-   [#inference](https://hashnode.com/tag/inference)
-   [#gateway-api](https://hashnode.com/tag/gateway-api)
-   [#ai-tools](https://hashnode.com/tag/ai-tools)
-   [#kubernetes](https://hashnode.com/tag/kubernetes)

## Written by

[Srujan Reddy](https://hashnode.com/@Srujan12)

@Srujan12 · Dallas, TX

  
[View profile](https://hashnode.com/@Srujan12)

Devops Engineer @Expedia

I am a Kubernetes Engineer passionate about leveraging Cloud Native ecosystem to run secure, efficient and effective workloads.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
