Synthetic Workload for LLM Serving

The dataset used in the paper is a synthetic workload, where clients send requests with different input and output lengths, and with varying request rates.

Data and Resources

Cite this as

Ying Sheng, Shiyi Cao, Dacheng Li, Banghua Zhu, Zhuohan Li, Danyang Zhuo, Joseph E. Gonzalez, Ion Stoica (2024). Dataset: Synthetic Workload for LLM Serving. https://doi.org/10.57702/uy35ic0d

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2401.00588
Author Ying Sheng
More Authors
Shiyi Cao
Dacheng Li
Banghua Zhu
Zhuohan Li
Danyang Zhuo
Joseph E. Gonzalez
Ion Stoica
Homepage https://arxiv.org/abs/2305.05920