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
- 14039
- Venue
- VLDB
- Year
- 2025
- Pagerank
- 4.6379617e-05
- Overall Rank
- 7,827 | 45.61%
- DOI
-
10.14778/3696435.3696439
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
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 |
| 34 |
Similarity Search in High Dimensions via Hashing |
1999 |
VLDB |
0.00076824554 |
| 210 |
Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph |
2019 |
VLDB |
0.00034086264 |
| 494 |
Milvus: A Purpose-Built Vector Data Management System |
2021 |
SIGMOD |
0.00021769407 |
| 730 |
AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data |
2020 |
VLDB |
0.00017443615 |
| 858 |
SRS: Solving c-Approximate Nearest Neighbor Queries in High Dimensional Euclidean Space with a Tiny Index |
2015 |
VLDB |
0.00015833075 |
| 1,617 |
PASE: PostgreSQL Ultra-High-Dimensional Approximate Nearest Neighbor Search Extension |
2020 |
SIGMOD |
0.0001113145 |
| 1,907 |
Fast and Unified Local Search for Random Walk Based K-Nearest-Neighbor Query in Large Graphs |
2014 |
SIGMOD |
0.00010130702 |
| 1,927 |
Efficient Processing of k Nearest Neighbor Joins using MapReduce |
2012 |
VLDB |
0.00010062395 |
| 1,966 |
LazyLSH: Approximate Nearest Neighbor Search for Multiple Distance Functions with a Single Index |
2016 |
SIGMOD |
9.9130791e-05 |
| 2,002 |
Efficient Approximate Nearest Neighbor Search in Multi-dimensional Databases |
2023 |
SIGMOD |
9.8258191e-05 |
| 2,264 |
Manu: A Cloud Native Vector Database Management System |
2022 |
VLDB |
9.1587362e-05 |
| 2,287 |
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search |
2024 |
SIGMOD |
9.1004806e-05 |
| 2,321 |
High-Throughput Vector Similarity Search in Knowledge Graphs |
2023 |
SIGMOD |
9.0359336e-05 |
| 2,687 |
HVS: Hierarchical Graph Structure Based on Voronoi Diagrams for Solving Approximate Nearest Neighbor Search |
2022 |
VLDB |
8.3079951e-05 |
| 2,772 |
High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations |
2023 |
SIGMOD |
8.1491893e-05 |
| 2,969 |
Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces |
2023 |
VLDB |
7.7955562e-05 |
| 4,869 |
Point-to-Hyperplane Nearest Neighbor Search Beyond the Unit Hypersphere |
2021 |
SIGMOD |
5.8588434e-05 |
| 5,763 |
Top-k Nearest Neighbor Search In Uncertain Data Series |
2015 |
VLDB |
5.3358283e-05 |
| 6,497 |
Progressive Top-K Nearest Neighbors Search in Large Road Networks |
2020 |
SIGMOD |
5.0324877e-05 |
| 7,198 |
ARKGraph: All-Range Approximate K-Nearest-Neighbor Graph |
2023 |
VLDB |
4.79852e-05 |
| 7,271 |
Exact Top-k Nearest Keyword Search in Large Networks |
2015 |
SIGMOD |
4.7764555e-05 |
| 9,307 |
Range-based Obstructed Nearest Neighbor Queries |
2016 |
SIGMOD |
4.3544778e-05 |
| 9,308 |
Optimal Spatial Dominance: An Effective Search of Nearest Neighbor Candidates |
2015 |
SIGMOD |
4.3544778e-05 |
| 9,309 |
Reverse k Nearest Neighbors Query Processing: Experiments and Analysis |
2015 |
VLDB |
4.3544778e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 10,122 |
TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware |
2026 |
SIGMOD |
4.1905499e-05 |
| 7,016 |
LLM for Data Management |
2024 |
VLDB |
4.8561622e-05 |
| 13,100 |
VecFlow-Chamfer: A GPU-based Data Management System for High-Performance Multi-Vector Search on Superchips |
2026 |
SIGMOD |
- |
| 9,454 |
An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models |
2024 |
VLDB |
4.3358002e-05 |
| 13,152 |
Database Perspective on LLM Inference Systems |
2025 |
VLDB |
- |
| 10,462 |
ScaleLLM: A Technique for Scalable LLM-augmented Data Systems |
2025 |
SIGMOD |
4.1905499e-05 |
| 10,222 |
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference |
2026 |
VLDB |
4.1905499e-05 |
| 10,711 |
Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal |
2025 |
VLDB |
4.1905499e-05 |
| 3,569 |
Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation |
2025 |
SIGMOD |
6.9588368e-05 |
| 10,170 |
From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation |
2026 |
SIGMOD |
4.1905499e-05 |