@article{hlstransformenergyefficientllama2, title = {HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis}, author = {Andy He and Darren Key and Mason Bulling and Andrew Chang and Skyler Shapiro and Everett Lee}, year = {2024}, eprint = {2405.00738}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.00738v1}, }