@article{superservefinegrainedinferenceservingfor, title = {SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads}, author = {Alind Khare and Dhruv Garg and Sukrit Kalra and Snigdha Grandhi and Ion Stoica and Alexey Tumanov}, year = {2023}, eprint = {2312.16733}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.16733v1}, }