arXiv (All)
open access
PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States
Linear-attention language models keep their context in a recurrent state of fixed size, where an inference system stores one copy of this state for every sequence it decodes at the same time. Storing the state at lower precision therefore lets more sequences share an accelerator. Existing state quan
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
- RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention#1355675
- Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity#1412406
- Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity#1394291
- RoleQ: Role-Aligned Scales for Converting Language Models to Ternary#1357463
- The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts#1051220
Record · ID 1414150
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