Jianwei Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianwei Dong has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Boxin Zhang
Tsinghua University, Beijing, China
2 shared publications - Chen Lin
Tsinghua University, Beijing, China
2 shared publications - Jiahao Wang
Hangzhou Dianzi University, Hangzhou, China and Approaching.AI, Beijing, China
2 shared publications - Jingqi Tang
Approaching.AI, Beijing, China
2 shared publications - Mingxing Zhang
Tsinghua University, Beijing, China
2 shared publications - Weiyu Xie
Tsinghua University, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 2 April 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (1) , 1-28
From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token. To mitigate this issue, existing solutions aim to reuse the preprocessed KVCache of each retrieved chunk to accelerate RAG. However, the lack of cross-chunk contextual information leads to a significant drop in generation quality, leaving the potential benefits of KVCache reuse largely unfulfilled. The challenge lies in how to reuse the precomputed KVCache chunk while preserving generation quality. We propose FusionRAG, a novel inference framework that optimizes both the preprocessing and reprocessing stages of RAG. In the offline preprocessing stage, we embed information from other related text chunks into each chunk, while in the online reprocessing stage, we recompute the KVCache for tokens that the model focuses on. As a result, we achieve a better trade-off between generation quality and efficiency. According to our experiments, FusionRAG significantly improves generation quality at the same recomputation ratio compared to previous state-of-the-art solutions. By recomputing fewer than 15% of the tokens, FusionRAG achieves up to 70% higher normalized-F1 scores than baselines and reduces TTFT by 2.66-9.39× compared to Full Attention.
- 2 April 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (1) , 1-28
Open AccessFrom Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token. To mitigate this issue, existing solutions aim to reuse the preprocessed KVCache of each retrieved chunk to accelerate RAG. However, the lack of cross-chunk contextual information leads to a significant drop in generation quality, leaving the potential benefits of KVCache reuse largely unfulfilled. The challenge lies in how to reuse the precomputed KVCache chunk while preserving generation quality. We propose FusionRAG, a novel inference framework that optimizes both the preprocessing and reprocessing stages of RAG. In the offline preprocessing stage, we embed information from other related text chunks into each chunk, while in the online reprocessing stage, we recompute the KVCache for tokens that the model focuses on. As a result, we achieve a better trade-off between generation quality and efficiency. According to our experiments, FusionRAG significantly improves generation quality at the same recomputation ratio compared to previous state-of-the-art solutions. By recomputing fewer than 15% of the tokens, FusionRAG achieves up to 70% higher normalized-F1 scores than baselines and reduces TTFT by 2.66-9.39× compared to Full Attention.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1014-1029
KTransformers: Unleashing the Full Potential of CPU/GPU Hybrid Inference for MoE Models
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1014-1029
Open AccessKTransformers: Unleashing the Full Potential of CPU/GPU Hybrid Inference for MoE Models