@article{202402.1702, doi = {10.20944/preprints202402.1702.v1}, url = {https://doi.org/10.20944/preprints202402.1702.v1}, year = 2024, month = {February}, publisher = {Preprints}, author = {Ditto PS and Jithin VG}, title = {Inference Acceleration for Large Language Models on CPUs}, journal = {Preprints} }