arXiv (All)
open access
When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression
Training-free KV-cache compression methods such as SnapKV, H2O, and PyramidKV evict tokens at the end of prefill, aiming to preserve the attention mass that future queries are expected to use -optimizing what to keep. We show that this objective fails in two distinct ways. (1) Compensation: restorin
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
- Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling#124007
- CVE-2026-97941 — HIGH 7.8#1098383
- CFS 43 Compilation of VGGT Submissions 30 June 2016#1133519
- Occam's Razor through Load Minimization Theory － Reinterpreting Simplicity as Compassionate Load Reduction －#726468
- CVE-2026-75805 — MEDIUM 5.3#1147582
Record · ID 1118046
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