@article{pipeinferacceleratingllminferenceusing, title = {PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation}, author = {Branden Butler and Sixing Yu and Arya Mazaheri and Ali Jannesari}, year = {2024}, eprint = {2407.11798}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.11798v2}, }