# LightSeq: A High Performance Inference Library for Transformers

arXiv: https://arxiv.org/abs/2010.13887 · HTML: https://mlsanity.com/paper/2010.13887/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

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

- [A Survey of Resource-efficient LLM and Multimodal Foundation Models](https://mlsanity.com/paper/2401.08092/) (2024)
- [How Far Are We From AGI: Are LLMs All We Need?](https://mlsanity.com/paper/2405.10313/) (2024)
- [Pie: Pooling CPU Memory for LLM Inference](https://mlsanity.com/paper/2411.09317/) (2024)
- [Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution](https://mlsanity.com/paper/2402.15678/) (2024)

## Abstract (arXiv)

Transformer, BERT and their variants have achieved great success in natural language processing. Since Transformer models are huge in size, serving these models is a challenge for real industrial applications. In this paper, we propose LightSeq, a highly efficient inference library for models in the Transformer family. LightSeq includes a series of GPU optimization techniques to to streamline the computation of neural layers and to reduce memory footprint. LightSeq can easily import models trained using PyTorch and Tensorflow. Experimental results on machine translation benchmarks show that LightSeq achieves up to 14x speedup compared with TensorFlow and 1.4x compared with FasterTransformer, a concurrent CUDA implementation. The code is available at https://github.com/bytedance/lightseq.