arXiv (All)
open access
A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention
The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing attention layers' RoPE positional embeddings with alternative decay-based mechanisms, which can then be used to prune KV-cache during inference. However, these decay functions have li
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
- LayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition#1233218
- Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG#1109499
- Decode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation#620451
- Decode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation#618772
- Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents#1202252
Record · ID 1233090
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