39 citations · 49 across the 5 of their papers we have counts for
Showing cs.DCShow all
2 papers · 1 filter
cs.DC2024★ 2 cited
FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines
Jiaao He, Jidong Zhai
Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is en…
cs.DC2019★ 8 cited
Heterogeneity-Aware Asynchronous Decentralized Training
Qinyi Luo, Jiaao He, Youwei Zhuo +1
Distributed deep learning training usually adopts All-Reduce as the synchronization mechanism for data parallel algorithms due to its high performance in homogeneous environment. H…