@article{multibinbatchingforincreasingllm, title = {Multi-Bin Batching for Increasing LLM Inference Throughput}, author = {Ozgur Guldogan and Jackson Kunde and Kangwook Lee and Ramtin Pedarsani}, year = {2024}, eprint = {2412.04504}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.04504v1}, }