arXiv CS
open access
RISK-KV: Quality-Aware Selective KV Cache Reconstruction for Distributed LLM Inference
Request migration and interruption recovery in distributed large language model (LLM) inference rely on historical key-value (KV) caches. Retaining or transferring a complete cache incurs substantial state overhead, whereas replaying historical tokens requires additional computation. This paper prop
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
- RISK-KV: Quality-Aware Selective KV Cache Reconstruction for Distributed LLM Inference#1414149
- Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following#1064998
- Fast Recovery for LLM Serving via Decoupled Device Memory Lifetime in Dynamo#1061091
- Fast Recovery for LLM Serving via Decoupled Device Memory Lifetime in Dynamo#1043071
- Throughput-Oriented LLM Inference via KV-Activation Hybrid Caching with a Single GPU#1326086
Record · ID 1406425
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