SubGCache reuses precomputed KV caches at the subgraph level for batches of graph RAG queries, cutting TTFT by up to 6.68x with comparable accuracy.
Batch processing of top-k spatial-textual queries.ACM Transactions on Spatial Algorithms and Systems (TSAS), 3 (4):1–40, 2018
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache
SubGCache reuses precomputed KV caches at the subgraph level for batches of graph RAG queries, cutting TTFT by up to 6.68x with comparable accuracy.