@article{accelgenheterogeneoussloguaranteedhigh, title = {AccelGen: Heterogeneous SLO-Guaranteed High-Throughput LLM Inference Serving for Diverse Applications}, author = {Haiying Shen and Tanmoy Sen}, year = {2025}, eprint = {2503.13737}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.13737v1}, }