arXiv CS
open access
CacheSmith: Accurate RAG Serving under Latency SLOs with Adaptive KV Reuse
This paper presents CacheSmith, a KV cache reuse system for RAG prefill that maximizes quality-gated SLO attainment. While context caching lowers prefill latency by reusing precomputed KV states for retrieved chunks, it misses cross-chunk attention that a full prefill would compute over concatenated
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- CacheSmith: Accurate RAG Serving under Latency SLOs with Adaptive KV Reuse#1344748
- Budgeted Cache Repair for Cross-Context KV-Cache Reuse#1186547
- ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving#246529
- Taming Subpacketization without Sacrificing Communication: A Packet Type-based Framework for D2D Coded Caching#1109785
- RASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution#1325555
Record · ID 1335971
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive