arXiv (All)
open access
ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression
Some observation-window-based KV cache compressors use prompt attention to identify important tokens but allocate uniform or predefined budgets across heads, overlooking input-dependent differences in budget demand. We propose ChampionKV, an input-adaptive head-wise budget allocator for long-context
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
- KVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression#1232850
- Read What Matters: Query-Adaptive Quantization for KV Caches#1248172
- AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning#1187685
- Tools-CC-Bench: a Benchmark Suite for Collective Communication with Compression in HPC and AI Workloads#1083219
- TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding#1355107
Record · ID 1343223
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