DBScholar

Back to papers

Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models

Summary: Chameleon: a disaggregated heterogeneous accelerator architecture pairing FPGA vector-search accelerators with GPU LLM inference and CPU coordinators to independently scale retrieval and inference. Prototype yields up to 2.16× latency reduction and 3.18× throughput speedup vs CPU–GPU baselines. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
h0f9f8a632e8789f8
Venue
VLDB
Year
2025
Pagerank
6.2420637e-05
Overall Rank
5,142 | 65.54%
DOI
10.14778/3696435.3696439
PDF
Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{jiang_vldb25,
        title = {{Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models}},
        author = {Jiang, Wenqi and Zeller, Marco and Waleffe, Roger and Hoefler, Torsten and Alonso, Gustavo},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {1},
        pages = {42--52},
        doi = {10.14778/3696435.3696439},
        url = {https://doi.org/10.14778/3696435.3696439},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 10 of 10 citing papers.

Rank Citing Paper Year Venue Pagerank
3,286 In-depth Analysis of Graph-based RAG in a Unified Framework 2025 VLDB 7.441688e-05
7,610 Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search 2026 SIGMOD 5.4683985e-05
8,364 Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal 2025 VLDB 5.3304544e-05
8,829 SwiftSpatial: Spatial Joins on Modern Hardware 2025 SIGMOD 5.2533436e-05
10,389 CatKV: Accelerating Position-Independent Caching with Context-Adaptive KV Cache Compression 2027 SIGMOD 4.9605343e-05
10,419 Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects 2027 VLDB 4.9605343e-05
10,503 CMANNS: GPU-Accelerated Graph Index Construction for ANNS via Compute-Memory Disaggregation 2026 SIGMOD 4.9605343e-05
10,780 Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search 2026 VLDB 4.9605343e-05
10,816 Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search 2026 VLDB 4.9605343e-05
11,365 LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation 2025 VLDB 4.9605343e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 24 of 24 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
20 Similarity Search in High Dimensions via Hashing 1999 VLDB 0.00057610161
75 Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph 2019 VLDB 0.00037163157
181 Milvus: A Purpose-Built Vector Data Management System 2021 SIGMOD 0.00026425782
325 AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data 2020 VLDB 0.00020930941
562 SRS: Solving c-Approximate Nearest Neighbor Queries in High Dimensional Euclidean Space with a Tiny Index 2015 VLDB 0.00016344855
802 RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search 2024 SIGMOD 0.00013822222
901 PASE: PostgreSQL Ultra-High-Dimensional Approximate Nearest Neighbor Search Extension 2020 SIGMOD 0.00013149954
1,165 Efficient Approximate Nearest Neighbor Search in Multi-dimensional Databases 2023 SIGMOD 0.00011708765
1,280 Manu: A Cloud Native Vector Database Management System 2022 VLDB 0.00011199537
1,371 High-Throughput Vector Similarity Search in Knowledge Graphs 2023 SIGMOD 0.00010874981
1,524 LazyLSH: Approximate Nearest Neighbor Search for Multiple Distance Functions with a Single Index 2016 SIGMOD 0.0001033427
1,601 High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations 2023 SIGMOD 0.00010092977
1,602 Fast and Unified Local Search for Random Walk Based K-Nearest-Neighbor Query in Large Graphs 2014 SIGMOD 0.00010091918
1,618 Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces 2023 VLDB 0.00010045437
1,684 HVS: Hierarchical Graph Structure Based on Voronoi Diagrams for Solving Approximate Nearest Neighbor Search 2022 VLDB 9.8770749e-05
2,183 Efficient Processing of k Nearest Neighbor Joins using MapReduce 2012 VLDB 8.8973287e-05
5,227 Point-to-Hyperplane Nearest Neighbor Search Beyond the Unit Hypersphere 2021 SIGMOD 6.2080477e-05
5,264 Top-k Nearest Neighbor Search In Uncertain Data Series 2015 VLDB 6.1929831e-05
5,891 ARKGraph: All-Range Approximate K-Nearest-Neighbor Graph 2023 VLDB 5.9396547e-05
6,073 Progressive Top-K Nearest Neighbors Search in Large Road Networks 2020 SIGMOD 5.8780393e-05
7,031 Exact Top-k Nearest Keyword Search in Large Networks 2015 SIGMOD 5.6000241e-05
8,382 Reverse k Nearest Neighbors Query Processing: Experiments and Analysis 2015 VLDB 5.3266895e-05
9,450 Range-based Obstructed Nearest Neighbor Queries 2016 SIGMOD 5.1613384e-05
9,451 Optimal Spatial Dominance: An Effective Search of Nearest Neighbor Candidates 2015 SIGMOD 5.1613384e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 4,729 LLM for Data Management 2024 VLDB
2 13,627 VecFlow-Chamfer: A GPU-based Data Management System for High-Performance Multi-Vector Search on Superchips 2026 SIGMOD
3 7,336 An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models 2024 VLDB
4 9,191 Database Perspective on LLM Inference Systems 2025 VLDB
5 5,376 RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference 2026 VLDB
6 11,229 ScaleLLM: A Technique for Scalable LLM-augmented Data Systems 2025 SIGMOD
7 10,960 RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems 2026 VLDB
8 8,364 Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal 2025 VLDB
9 2,197 Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation 2025 SIGMOD
10 10,718 From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation 2026 SIGMOD