REVIEW 19 cited by
RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation
read the original abstract
Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, RAG introduces long sequence generation and leads to high computation and memory costs. We propose RAGCache, a novel multilevel dynamic caching system tailored for RAG. Our analysis benchmarks current RAG systems, pinpointing the performance bottleneck (i.e., long sequence due to knowledge injection) and optimization opportunities (i.e., caching knowledge's intermediate states). Based on these insights, we design RAGCache, which organizes the intermediate states of retrieved knowledge in a knowledge tree and caches them in the GPU and host memory hierarchy. RAGCache proposes a replacement policy that is aware of LLM inference characteristics and RAG retrieval patterns. It also dynamically overlaps the retrieval and inference steps to minimize the end-to-end latency. We implement RAGCache and evaluate it on vLLM, a state-of-the-art LLM inference system and Faiss, a state-of-the-art vector database. The experimental results show that RAGCache reduces the time to first token (TTFT) by up to 4x and improves the throughput by up to 2.1x compared to vLLM integrated with Faiss.
Forward citations
Cited by 19 Pith papers
-
Models Take Notes at Prefill: KV Cache Can Be Editable and Composable
KV caches function as notebooks of prefilled conclusions, enabling field-level edits that recover decisions (especially with CoT) and position-portable skill composition with near-identical outputs at O(L) cost.
-
LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
LazyAttention kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV cache reuse, delivering 1.37× lower TTFT and 1.40× higher throughput than Block-Attention under skewed document distribut...
-
Efficient Remote KV Cache Reuse with GPU-native Video Codec
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
-
Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory
Long-context memory can be organized by caching intermediate residual states and recomputing only query-conditioned upper layers over a bounded retrieved pack.
-
FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents
Dependency-checked answer reuse lets FinCacheServe skip about 53% of LLM calls in hosted SEC-derived RAG traces without serving any observed stale outputs.
-
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
FCGraft synthesizes code policies for embodied agents by grafting KV caches from a library of validated functions, claiming 18.31% higher success rate and 2.3x faster synthesis than prompt-level caching.
-
Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
GroundedCache reduces unsafe-served rate in RAG answer caching to 0-1.5% (vs 15-51.5% naive) via four validation gates while keeping p50 latency within 1.07x of no-cache baseline.
-
Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation
A latent-space reasoning cache with a lightweight decoder cuts the cost of LLM-based human mobility simulation by roughly 40-90% while keeping trajectory quality comparable.
-
AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.
-
CacheClip: Accelerating RAG with Effective KV Cache Reuse
CacheClip accelerates RAG prefill by up to 3.33x via auxiliary-model-guided selective KV recomputation while retaining 85-91% of full-attention quality on NIAH and LongBench.
-
BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
BatchLLM achieves 1.3x-10.8x higher throughput than vLLM and SGLang for batched LLM inference with prefix sharing via global prefix identification, decoding-first reordering, and memory-centric token batching.
-
Retrieval-Augmented Generation for Natural Language Processing: A Survey
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
-
KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems
KAP compiles structured knowledge priors into runtime access plans that cut proposal-time KV access to 5.5% at 128K while matching full-context QA quality and yielding up to 1.19× decode throughput.
-
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
By reusing validated function-level KV caches (stitching) and regenerating only localized error spans (patching), FCGraft makes CodeLLM policies for embodied agents faster and more robust than prompt-level caching.
-
SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance
SIFT precomputes selective attention indices via local and cross-attention invariance to speed RAG prefill 1.71x while keeping accuracy within 1% of full recompute, storing only bit vectors 24,000x smaller than KV tensors.
-
Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
Temporal semantic caching and MCP workflow optimizations deliver 30.6x median speedup on cache hits and 1.67x overall speedup with 40% latency reduction on the AssetOpsBench industrial agent benchmark.
-
ConceptBot: Enhancing Robot's Autonomy through Task Decomposition with Large Language Models and Knowledge Graph
Using ConceptNet-augmented prompts, ConceptBot reports 87% vs 31% success on implicit tasks and 76% vs 15% on risk-aware tasks over a re-implemented SayCan baseline, with an 80% SafeAgentBench score.
-
From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
-
MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems
The authors claim their MultiFluxAI orchestration framework achieves 95% accuracy and 0-10 ms responses by combining rule-based routing, caching, and graph knowledge stores for multi-service RAG queries.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.