Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation

Summary: Cache-Craft uses chunk-caches to reuse K/Vs in RAG, reducing repeated attention. It spots reusable chunk-caches, performs targeted recomputation to preserve quality, and hardware eviction to maximize reuse; reports 51% recomputation reduction and up to 2x throughput on LLaMA models. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 7209
Venue: SIGMOD
Year: 2025
Pagerank: 6.9588368e-05
Overall Rank: 3,569 | 75.20%
DOI: 10.1145/3725273

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,933	In-depth Analysis of Graph-based RAG in a Unified Framework	2025	VLDB	4.6089395e-05
10,066	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD	4.1905499e-05
10,170	From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation	2026	SIGMOD	4.1905499e-05

Outgoing Citations (Sorted by Pagerank)

Showing 7 of 7 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
430	Approximate Query Processing: Taming the TeraBytes! A Tutorial	2001	VLDB	0.00023406426
1,161	VerdictDB: Universalizing Approximate Query Processing	2018	SIGMOD	0.00013579831
1,368	SlimDB: A Space-Efficient Key-Value Storage Engine For Semi-Sorted Data	2017	VLDB	0.0001235708
4,193	New Trends in High-D Vector Similarity Search: AI-driven, Progressive, and Distributed	2021	VLDB	6.3657766e-05
5,046	Put an Elephant into a Fridge: Optimizing Cache Efficiency for In-memory Key-value Stores	2020	VLDB	5.7322889e-05
6,359	High-Dimensional Vector Similarity Search: From Time Series to Deep Network Embeddings	2020	SIGMOD	5.0912204e-05
7,232	Catalyst: Optimizing Cache Management for Large In-memory Key-value Systems	2023	VLDB	4.7891237e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
10,718	Cracking Vector Search Indexes	2025	VLDB	4.1905499e-05
10,386	Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs	2025	SIGMOD	4.1905499e-05
7,933	In-depth Analysis of Graph-based RAG in a Unified Framework	2025	VLDB	4.6089395e-05
10,222	RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference	2026	VLDB	4.1905499e-05
6,970	AquaPipe: A Quality-Aware Pipeline for Knowledge Retrieval and Large Language Models	2025	SIGMOD	4.8740302e-05
10,020	HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems	2026	SIGMOD	4.1905499e-05
13,149	ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models	2025	VLDB	-
6,350	PQCache: Product Quantization-based KVCache for Long Context LLM Inference	2025	SIGMOD	5.0957601e-05
10,066	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD	4.1905499e-05
10,170	From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation	2026	SIGMOD	4.1905499e-05