Zaifeng Pan

Orcid: 0000-0002-6759-2616

According to our database1, Zaifeng Pan authored at least 11 papers between 2021 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving.
CoRR, July, 2025

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows.
CoRR, July, 2025

PluS: Highly Efficient and Expandable ML Compiler with Pluggable Graph Schedules.
Proceedings of the 2025 USENIX Annual Technical Conference, 2025

WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training.
Proceedings of the 19th USENIX Symposium on Operating Systems Design and Implementation, 2025

2024
Compressed data direct computing for Chinese dataset on DCU.
CCF Trans. High Perform. Comput., April, 2024

RecFlex: Enabling Feature Heterogeneity-Aware Optimization for Deep Recommendation Models with Flexible Schedules.
Proceedings of the International Conference for High Performance Computing, 2024

2023
BladeDISC: Optimizing Dynamic Shape Machine Learning Workloads via Compiler Approach.
Proc. ACM Manag. Data, September, 2023

RECom: A Compiler Approach to Accelerating Recommendation Model Inference with Massive Embedding Columns.
Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2023

2022
Exploring Data Analytics Without Decompression on Embedded GPU Systems.
IEEE Trans. Parallel Distributed Syst., 2022

G-SLIDE: A GPU-Based Sub-Linear Deep Learning Engine via LSH Sparsification.
IEEE Trans. Parallel Distributed Syst., 2022

2021
G-TADOC: Enabling Efficient GPU-Based Text Analytics without Decompression.
Proceedings of the 37th IEEE International Conference on Data Engineering, 2021


  Loading...