---
title: "LoRA: Low-Rank Adaptation of Large Language Models"
description: "LoRA is the cleanest first paper for understanding efficient model adaptation. It turns fine-tuning into small low-rank update matrices, which connects directly to Fanout's model training and serving material."
canonical_url: "https://fanout.sh/daily/2026-07-12-lora"
md_url: "https://fanout.sh/daily/2026-07-12-lora.md"
last_updated: "2026-07-12"
access: "public"
---

# LoRA: Low-Rank Adaptation of Large Language Models

LoRA is the cleanest first paper for understanding efficient model adaptation. It turns fine-tuning into small low-rank update matrices, which connects directly to Fanout's model training and serving material.

## Paper details

- Authors: Hu et al.

- Venue: ICLR 2022

- Track: Inference

- Difficulty: Easy

- Reading time: 35 min

- Original paper: https://arxiv.org/abs/2106.09685

## What you will learn

- Why freezing the base model can still allow useful task adaptation.

- How a low-rank update changes parameter count and storage cost.

- Why adapter serving becomes a systems problem after training works.

## Continue exploring

[Explore LoRA](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Alora): Open the Fanout LoRA node and connect low-rank adaptation to fine-tuning, QLoRA, PEFT, and adapter serving.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md