arXiv (All)
open access
Shared Stopping Decisions Change Answers in HQQ Cache Quantization
Language-model systems batch questions for throughput, but unrelated questions should not change a target's answer when its input and numerical execution are fixed. We study compression of the key and value cache, which stores attention representations reused during generation. With request-local gr
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
- The Role of Concepts in Fixing Language#765701
- Syllabic priming in lexical decision and naming tasks: The syllable congruency effect re-examined in French.#68224
- Effects of Auditory and Motor Cues on Syntactic Planning during Sentence Production in Free- and Fixed-Word-Order Languages: Evidence from Hindi and English#393505
- Prioritized Imperatives and Normative Conflicts#743508
- Minimal propositions and real world utterances#777130
Record · ID 1202670
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