Siyuan Sun, Zhaojia Wang, Hanshuo Liu, Jiehan Zhou. SmartBatchLLM: An efficient adaptive hybrid batching strategy for large language model serving. // Parallel Computing. – 2026. – DOI: 10.1016/j.parco.2026.103216. – URL: https://doi.org/10.1016/j.parco.2026.103216
Siyuan Sun, Zhaojia Wang, Hanshuo Liu, & Jiehan Zhou (2026). SmartBatchLLM: An efficient adaptive hybrid batching strategy for large language model serving. Parallel Computing. https://doi.org/10.1016/j.parco.2026.103216
Siyuan Sun, et al. “SmartBatchLLM: An efficient adaptive hybrid batching strategy for large language model serving.” Parallel Computing, 2026. doi:10.1016/j.parco.2026.103216.
@article{Sun2026,
title = {SmartBatchLLM: An efficient adaptive hybrid batching strategy for large language model serving},
author = {Sun, Siyuan and Wang, Zhaojia and Liu, Hanshuo and Zhou, Jiehan},
journal = {Parallel Computing},
year = {2026},
doi = {10.1016/j.parco.2026.103216},
url = {https://doi.org/10.1016/j.parco.2026.103216}
}