---
title: "Discussion on \"How vLLM does it?\" | Hashnode"
description: "Discussion on \"How vLLM does it?\". TL;DR Let's understand PagedAttention & Continuous Batching"
url: "https://hashnode.com/posts/how-vllm-does-it/67ffe87c732e99953e08e9c4"
---

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

Discussion

# [How vLLM does it?](https://rishirajacharya.hashnode.dev/how-vllm-does-it?utm_source=hashnode&utm_medium=feed)

TL;DR Let's understand PagedAttention & Continuous Batching

Apr 16, 2025 · 9 min read · rishirajacharya.hashnode.dev  
Read the article

-   [#vllm](https://hashnode.com/tag/vllm)
-   [#llm](https://hashnode.com/tag/llm)
-   [#generative-ai](https://hashnode.com/tag/generative-ai)

## Written by

[Rishiraj Acharya](https://hashnode.com/@rishirajacharya)

@rishirajacharya · Kolkata, India

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

Google Developer Expert in ML | Hugging Face Fellow | GSoC at TensorFlow | TFUG Kolkata Organizer | Kaggle Master | IntelliTek ML Engineer

Rishiraj is a triple Google Developer Expert (AI, Cloud & Kaggle). He is a Machine Learning Engineer at Intellitek, worked at Tensorlake, Dynopii & Celebal in the past and is a Hugging Face 🤗 Fellow. He is the organizer of TensorFlow User Group Kolkata and has been a Google Summer of Code contributor at TensorFlow. He is a Kaggle Competitions Master and has been a KaggleX BIPOC Grant Mentor. Rishiraj specializes in the domain of Natural Language Processing and Speech Technologies and works with AI for Medicine.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.