arXiv (All)
open access
DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression
Long-context large language models (LLMs) have demonstrated strong capabilities across a wide range of tasks, but the growing KV cache introduces substantial memory and inference overhead. Existing one-shot KV cache compression methods typically commit to irreversible eviction immediately after pref
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
- A Simple Plug-in for Improving Eviction-Based KV Cache Compression#1344588
- Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding#972808
- CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models#665868
- CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models#664368
- Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models#1354054
Record · ID 1202705
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