arXiv (All)
open access
RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention
Multi-head latent attention (MLA) compresses the content of a key-value cache into a shared latent per token, making low-bit storage attractive for long-context inference. At two bits, errors in this representation perturb both attention matching and value readout, with effects that depend on error
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
- KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding#321808
- Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference#1116994
- Head pursuit: Probing attention specialization in multimodal transformers#442708
- Multi-Head Self Attention is a Parameter Identification Mechanism#821187
- Task Context Shapes Component Roles in Language Models#1298391
Record · ID 1355675
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