---
author: "Umesh Malik"
canonical: "https://umesh-malik.com/blog/tag/pytorch"
description: "Explore articles tagged with PyTorch by Umesh Malik — AI Engineer, LLM & GenAI Developer. Learn PyTorch best practices, practical tips, and in-depth guides."
title: "Umesh Malik's Blog - PyTorch Articles | PyTorch Tutorials"
tokens: 146
generator: "scripts/generate-page-markdown.mjs"
---

[← Back to Blog](https://umesh-malik.com/blog)

# PyTorch

1 article

 [![Cover comparing modern LLM architectures across sixteen single-file PyTorch reference implementations](https://umesh-malik.com/blog/compare-llm-architectures-pytorch-cover.png)

LLM Engineering • Sep 14, 2026

### How to Compare LLM Architectures: 16 Models, One File Each

Compare LLM architectures fast: GQA cuts KV cache 8x on Llama 3 70B, MLA cuts it 93.3% on DeepSeek-V2. One PyTorch repo shows why, file by file.

8 min read

Read more →](https://umesh-malik.com/blog/compare-llm-architectures-pytorch)