# Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

arXiv: https://arxiv.org/abs/2410.08791 · HTML: https://mlsanity.com/paper/2410.08791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models](https://mlsanity.com/paper/2102.07988/) (2021)
- [ReLU2 Wins: Discovering Efficient Activation Functions for Sparse LLMs](https://mlsanity.com/paper/2402.03804/) (2024)
- [Compressing LLMs: The Truth is Rarely Pure and Never Simple](https://mlsanity.com/paper/2310.01382/) (2023)
- [SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks](https://mlsanity.com/paper/1801.04380/) (2018)
- [Intriguing Properties of Quantization at Scale](https://mlsanity.com/paper/2305.19268/) (2023)
- [Norm Tweaking: High-performance Low-bit Quantization of Large Language Models](https://mlsanity.com/paper/2309.02784/) (2023)
- [Alternating Updates for Efficient Transformers](https://mlsanity.com/paper/2301.13310/) (2023)

## Abstract (arXiv)

The rapid growth in machine learning models, especially in natural language processing and computer vision, has led to challenges when running these models on hardware with limited resources. This paper introduces Superpipeline, a new framework designed to optimize the execution of large AI models on constrained hardware during both training and inference. Our approach involves dynamically managing model execution by dividing models into individual layers and efficiently transferring these layers between GPU and CPU memory. Superpipeline reduces GPU memory usage by up to 60% in our experiments while maintaining model accuracy and acceptable processing speeds. This allows models that would otherwise exceed available GPU memory to run effectively. Unlike existing solutions that focus mainly on inference or specific model types, Superpipeline can be applied to large language models (LLMs), vision-language models (VLMs), and vision-based models. We tested Superpipeline's performance across various models and hardware setups. The method includes two key parameters that allow fine-tuning the balance between GPU memory use and processing speed. Importantly, Superpipeline does not require retraining or changing model parameters, ensuring that the original model's output remains unchanged. Superpipeline's simplicity and flexibility make it useful for researchers and professionals working with advanced AI models on limited hardware. It enables the use of larger models or bigger batch sizes on existing hardware, potentially speeding up innovation across many machine learning applications. This work marks an important step toward making advanced AI models more accessible and optimizing their deployment in resource-limited environments. The code for Superpipeline is available at https://github.com/abbasiReza/super-pipeline.