most citedFastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

2 citations · 2 across the 2 of their papers we have counts for

collaborators

1 paper

cs.LG2022

OLLIE: Derivation-based Tensor Program Optimizer

Liyan Zheng, Haojie Wang, Jidong Zhai +7

Boosting the runtime performance of deep neural networks (DNNs) is critical due to their wide adoption in real-world tasks. Existing approaches to optimizing the tensor algebra exp…