RaBitQCache proposes rotated binary quantization with binary-INT4 arithmetic for unbiased attention weight estimation in long-context LLMs, enabling adaptive Top-p retrieval and hardware optimizations.
arXiv preprint arXiv:2601.20326 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
RaBitQCache proposes rotated binary quantization with binary-INT4 arithmetic for unbiased attention weight estimation in long-context LLMs, enabling adaptive Top-p retrieval and hardware optimizations.