News

Dec 21, 2024 One paper on GPU cluster scheduling is accepted by TACO.
Dec 20, 2024 One paper on GPU resource pooling is accepted by IPDPS 2025.
Dec 16, 2024 The RetrievalAttention work wins the best paper award of the 4th NeurIPS Workshop on Efficient Natural Language and Speech Processing.
Oct 10, 2024 The RetrievalAttention work is accepted by the 4th NeurIPS Workshop on Efficient Natural Language and Speech Processing (ENLSP).
Sep 16, 2024 RetrievalAttention on accelerating long-context LLM Inference is released on arXiv.
Jun 21, 2024 Our poster on LLM Inference is awarded the Best Poster Award on IWQoS’24.
Jun 11, 2024 FedCA on Federated Learning is accepted by ICPP’24.
Apr 15, 2024 PAS on Federated Learning is accepted by IWQoS’24.
Mar 21, 2024 Parrot on accelerating LLM inference via the abstraction of Semantic Variable is accepted by OSDI’24.
Dec 01, 2023 One paper on Federated Learning accepted by INFOCOM’24.
Jan 25, 2023 APF accepted to IEEE Trans. Parallel and Distributed Systems as an extended version of ICDCS ’21.
Nov 30, 2022 GIFT accepted to JSAC, special issue on Communication-Efficient Distributed Learning over Networks.
Sep 09, 2022 Proposal funded by National Natural Science Foundation of China (Youth Program).
Jun 30, 2022 Awarded CCF-Huawei Populus Grove Fund.
Jan 01, 2022 Started my career at SJTU as an associate professor.