@article{halohardwareawarequantizationwithlow, title = {HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration}, author = {Rohan Juneja and Shivam Aggarwal and Safeen Huda and Tulika Mitra and Li-Shiuan Peh}, year = {2025}, eprint = {2502.19662}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.19662v2}, }