@article{demystifyingplatformrequirementsfor, title = {Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models}, author = {Abhimanyu Bambhaniya and Ritik Raj and Geonhwa Jeong and Souvik Kundu and Sudarshan Srinivasan and Suvinay Subramanian and Midhilesh Elavazhagan and Madhu Kumar and Tushar Krishna}, year = {2024}, eprint = {2406.01698}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.01698v3}, }