@article{automatedheterogeneouslowbitquantization, title = {Automated Heterogeneous Low-Bit Quantization of Multi-Model Deep Learning Inference Pipeline}, author = {Jayeeta Mondal and Swarnava Dey and Arijit Mukherjee}, year = {2023}, eprint = {2311.05870}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.05870v1}, }