# Fast and Memory-Efficient Neural Code Completion

arXiv: https://arxiv.org/abs/2004.13651 · HTML: https://mlsanity.com/paper/2004.13651/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 30 of 38)

- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [Productivity Assessment of Neural Code Completion](https://mlsanity.com/paper/2205.06537/) (2022)
- [Leveraging Automated Unit Tests for Unsupervised Code Translation](https://mlsanity.com/paper/2110.06773/) (2021)
- [DOBF: A Deobfuscation Pre-Training Objective for Programming Languages](https://mlsanity.com/paper/2102.07492/) (2021)
- [CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation](https://mlsanity.com/paper/2501.08200/) (2025)
- [Using Large Language Models to Generate JUnit Tests: An Empirical Study](https://mlsanity.com/paper/2305.00418/) (2023)
- [CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences](https://mlsanity.com/paper/2202.06689/) (2022)
- [SpreadsheetCoder: Formula Prediction from Semi-structured Context](https://mlsanity.com/paper/2106.15339/) (2021)
- [SALLM: Security Assessment of Generated Code](https://mlsanity.com/paper/2311.00889/) (2023)
- [Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs](https://mlsanity.com/paper/2103.09499/) (2021)
- [A Survey on Machine Learning Techniques for Source Code Analysis](https://mlsanity.com/paper/2110.09610/) (2021)
- [CoCoSoDa: Effective Contrastive Learning for Code Search](https://mlsanity.com/paper/2204.03293/) (2022)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models](https://mlsanity.com/paper/2206.11719/) (2022)
- [From Commit Message Generation to History-Aware Commit Message Completion](https://mlsanity.com/paper/2308.07655/) (2023)
- [Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion](https://mlsanity.com/paper/2306.00381/) (2023)
- [FRANC: A Lightweight Framework for High-Quality Code Generation](https://mlsanity.com/paper/2307.08220/) (2023)
- [A Large-Scale Exploit Instrumentation Study of AI/ML Supply Chain Attacks in Hugging Face Models](https://mlsanity.com/paper/2410.04490/) (2024)
- [Energy-Based Models for Code Generation under Compilability Constraints](https://mlsanity.com/paper/2106.04985/) (2021)
- [All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs](https://mlsanity.com/paper/2205.10692/) (2022)
- [Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing](https://mlsanity.com/paper/2305.18584/) (2023)
- [Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey](https://mlsanity.com/paper/2310.17903/) (2023)
- [The Fault in our Stars: Quality Assessment of Code Generation Benchmarks](https://mlsanity.com/paper/2404.10155/) (2024)
- [Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models](https://mlsanity.com/paper/2104.01642/) (2021)
- [Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models](https://mlsanity.com/paper/2106.13928/) (2021)
- [A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks](https://mlsanity.com/paper/2312.15614/) (2023)
- [Full Line Code Completion: Bringing AI to Desktop](https://mlsanity.com/paper/2405.08704/) (2024)
- [Learning to Extend Program Graphs to Work-in-Progress Code](https://mlsanity.com/paper/2105.14038/) (2021)

## Abstract (arXiv)

Code completion is one of the most widely used features of modern integrated development environments (IDEs). While deep learning has made significant progress in the statistical prediction of source code, state-of-the-art neural network models consume hundreds of megabytes of memory, bloating the development environment. We address this in two steps: first we present a modular neural framework for code completion. This allows us to explore the design space and evaluate different techniques. Second, within this framework we design a novel reranking neural completion model that combines static analysis with granular token encodings. The best neural reranking model consumes just 6 MB of RAM, - 19x less than previous models - computes a single completion in 8 ms, and achieves 90% accuracy in its top five suggestions.