@article{batchmaxhigherllmthroughputusinglarger,
  title = {Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression},
  author = {Michael R. Metel and Boxing Chen and Mehdi Rezagholizadeh},
  year = {2024},
  eprint = {2412.05693},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.05693v1},
}