Hanfei Yu

22 papers A* 2A 3Journal 10Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Accelerating ML Inference via Opportunistic Pre-Loading on Serverless Clusters.
IEEE Trans. Parallel Distributed Syst.
Yifan Sui, Hanfei Yu, Yitao Hu, Jianxun Li, Hao Wang
2026 J jnl
MoEless: Efficient MoE LLM Serving via Serverless Computing.
CoRR
Hanfei Yu, Bei Ouyang, Shwai He, Ang Li, Hao Wang
2026 J jnl
RLHFless: Serverless Computing for Efficient RLHF.
CoRR
Rui Wei, Hanfei Yu, Shubham Jain, Yogarajan Sivakumar, Devesh Tiwari, Jian Li, Seung-Jong Park, Hao Wang
2026 A conf
Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading.
EuroSys
Hanfei Yu, Xingqi Cui, Hong Zhang, Hao Wang, Hao Wang
2026 J jnl
The Diminishing Returns of Early-Exit Decoding in Modern LLMs.
CoRR
Rui Wei, Rui Du, Hanfei Yu, Devesh Tiwari, Jian Li, Zhaozhuo Xu, Hao Wang
2025 — conf
Multi-Agent Reinforcement Learning with Serverless Computing.
SoCC
Rui Wei, Hanfei Yu, Xikang Song, Jian Li, Devesh Tiwari, Ying Mao, Hao Wang
2025 J jnl
ServerlessLoRA: Minimizing Latency and Cost in Serverless Inference for LoRA-Based LLMs.
CoRR
Yifan Sui, Hao Wang, Hanfei Yu, Yitao Hu, Jianxun Li, Hao Wang
2025 J jnl
fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving.
CoRR
Hanfei Yu, Xingqi Cui, Hong Zhang, Hao Wang, Hao Wang
2024 A* conf
Cheaper and Faster: Distributed Deep Reinforcement Learning with Serverless Computing.
AAAI
Hanfei Yu, Jian Li, Yang Hua, Xu Yuan, Hao Wang
2024 J jnl
Freyr $^+$+: Harvesting Idle Resources in Serverless Computing via Deep Reinforcement Learning.
IEEE Trans. Parallel Distributed Syst.
Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, Seung-Jong Park
2024 J jnl
Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing.
Proc. VLDB Endow.
Hanfei Yu, Jacob Carter, Hao Wang, Devesh Tiwari, Jian Li, Seung-Jong Park
2024 — conf
Pre-Warming is Not Enough: Accelerating Serverless Inference With Opportunistic Pre-Loading.
SoCC
Yifan Sui, Hanfei Yu, Yitao Hu, Jianxun Li, Hao Wang
2024 — conf
RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing.
ASPLOS (1)
Hanfei Yu, Rohan Basu Roy, Christian Fontenot, Devesh Tiwari, Jian Li, Hong Zhang, Hao Wang, Seung-Jong Park
2024 A conf
Stellaris: Staleness-Aware Distributed Reinforcement Learning with Serverless Computing.
SC
Hanfei Yu, Hao Wang, Devesh Tiwari, Jian Li, Seung-Jong Park
2023 A conf
Libra: Harvesting Idle Resources Safely and Timely in Serverless Clusters.
HPDC
Hanfei Yu, Christian Fontenot, Hao Wang, Jian Li, Xu Yuan, Seung-Jong Park
2022 A* conf
Accelerating Serverless Computing by Harvesting Idle Resources.
WWW
Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, Seung-Jong Park
2021 — conf
Enhancing Observability of Serverless Computing with the Serverless Application Analytics Framework.
ICPE (Companion)
Robert Cordingly, Navid Heydari, Hanfei Yu, Varik Hoang, Zohreh Sadeghi, Wes Lloyd
2021 — conf
FaaSRank: Learning to Schedule Functions in Serverless Platforms.
ACSOS
Hanfei Yu, Athirai A. Irissappane, Hao Wang, Wes J. Lloyd
2021 J jnl
Harvesting Idle Resources in Serverless Computing via Reinforcement Learning.
CoRR
Hanfei Yu, Hao Wang, Jian Li, Seung-Jong Park
2020 — conf
Implications of Programming Language Selection for Serverless Data Processing Pipelines.
DASC/PiCom/CBDCom/CyberSciTech
Robert Cordingly, Hanfei Yu, Varik Hoang, David Perez, David Foster, Zohreh Sadeghi, Rashad Hatchett, Wes J. Lloyd
2020 J jnl
Leveraging GPT-2 for Classifying Spam Reviews with Limited Labeled Data via Adversarial Training.
CoRR
Athirai A. Irissappane, Hanfei Yu, Yankun Shen, Anubha Agrawal, Gray Stanton
2020 — conf
The Serverless Application Analytics Framework: Enabling Design Trade-off Evaluation for Serverless Software.
WOSC@Middleware
Robert Cordingly, Hanfei Yu, Varik Hoang, Zohreh Sadeghi, David Foster, David Perez, Rashad Hatchett, Wes Lloyd