Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads

Read full text
Authors: Mert Hidayetoğlu, Aurick Qiao, Michael Wyatt, Jeff Rasley, Yuxiong He, Samyam Rajbhandari
Cited by: 3
References: 3

Fields of Study & Subjects

Software System Performance and Reliability Parallel Computing and Optimization Techniques Cloud Computing and Resource Management

Publication details

Journal / source
Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2
Publisher
ACM
Pages
1749–1763
Publication date
10 March 2026