Publications

(2024). Exploring CXL-based KV Cache Storage for LLM Serving. To appear (NIPS 2024 ML for Systems Workshop).

(2024). PULSE: Accelerating Distributed Pointer-Traversals on Disaggregated Memory. To appear (ASPLOS 2025).

(2024). Exploring Performance and Cost Optimization with ASIC-Based CXL Memory. Proceedings of the Nineteenth European Conference on Computer Systems (EuroSys 24 Best Paper Runner-Up).

PDF Cite Code DOI

(2023). SHEPHERD: Serving DNNs in the Wild. 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23).

PDF Cite

(2022). Jiffy: Elastic Far-Memory for Stateful Serverless Analytics. Proceedings of the Seventeenth European Conference on Computer Systems(EuroSys 22).

PDF Cite Code DOI

(2021). MIND: In-Network Memory Management for Disaggregated Data Centers. Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles(SOSP 21).

PDF Cite Code DOI

(2021). Caerus: NIMBLE Task Scheduling for Serverless Analytics. 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21).

PDF Cite