# Full Line Code Completion: Bringing AI to Desktop

arXiv: https://arxiv.org/abs/2405.08704 · HTML: https://mlsanity.com/paper/2405.08704/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 74 references that are in the map.
- First posted on arXiv 14 May 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [CodeGen2: Lessons for Training LLMs on Programming and Natural Languages](https://mlsanity.com/paper/2305.02309/) (2023)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [Fast and Memory-Efficient Neural Code Completion](https://mlsanity.com/paper/2004.13651/) (2020)
- [Program Synthesis and Semantic Parsing with Learned Code Idioms](https://mlsanity.com/paper/1906.10816/) (2019)
- [All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs](https://mlsanity.com/paper/2205.10692/) (2022)
- [Practitioners' Expectations on Code Completion](https://mlsanity.com/paper/2301.03846/) (2023)
- [Towards Full-line Code Completion with Neural Language Models](https://mlsanity.com/paper/2009.08603/) (2020)
- [A Study of Potential Code Borrowing and License Violations in Java Projects on GitHub](https://mlsanity.com/paper/2002.05237/) (2020)
- [The IntelliJ Platform: a Framework for Building Plugins and Mining Software Data](https://mlsanity.com/paper/2110.00141/) (2021)

## Built on by (most cited first, 4 of 4)

- [Enhancing Project-Specific Code Completion by Inferring Internal API Information](https://mlsanity.com/paper/2507.20888/) (2025)
- [Mellum: Production-Grade in-IDE Contextual Code Completion with Multi-File Project Understanding](https://mlsanity.com/paper/2510.05788/) (2025)
- [TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs](https://mlsanity.com/paper/2508.02455/) (2025)
- [Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model](https://mlsanity.com/paper/2510.08610/) (2025)

## Abstract (arXiv)

In recent years, several industrial solutions for the problem of multi-token code completion appeared, each making a great advance in the area but mostly focusing on cloud-based runtime and avoiding working on the end user's device. In this work, we describe our approach for building a multi-token code completion feature for the JetBrains' IntelliJ Platform, which we call Full Line Code Completion. The feature suggests only syntactically correct code and works fully locally, i.e., data querying and the generation of suggestions happens on the end user's machine. We share important time and memory-consumption restrictions, as well as design principles that a code completion engine should satisfy. Working entirely on the end user's device, our code completion engine enriches user experience while being not only fast and compact but also secure. We share a number of useful techniques to meet the stated development constraints and also describe offline and online evaluation pipelines that allowed us to make better decisions. Our online evaluation shows that the usage of the tool leads to 1.3 times more Python code in the IDE being produced by code completion. The described solution was initially started with a help of researchers and was then bundled into all JetBrains IDEs where it is now used by millions of users. Thus, we believe that this work is useful for bridging academia and industry, providing researchers with the knowledge of what happens when complex research-based solutions are integrated into real products.