arXiv (All)
open access
PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention
At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by memory bandwidth. Sparse attention reads only a subset of keys chosen by a cheap score estimate, and most methods give the unread tokens zero weigh
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
- SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference#1050008
- Preisach Attention: A Hysteretic Model of Sequential Memory#222606
- Instruction Retrieval at Inference Time for Small Language Models#1142567
- Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models#985228
- Frequency Modulation Detection Thresholds are Unrelated to Individual Differences in Verbal Memory Capacity.#4292
Record · ID 1118819
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