FlagRot: Selective Rotation for Low-Bit KV Caches
cs.CL, cs.AI, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Comments: 26 pages, 5 figures. Code: https://github.com/KunmingSHAO/FlagRot_releaser
Code: https://github.com/KunmingSHAO/FlagRot_releaser
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Phi-4 Technical Report
- WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms
- Training Verifiers to Solve Math Word Problems
- Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
- Gemma 3 Technical Report
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- PolarQuant: Quantizing KV Caches with Polar Transformation
- Mistral 7B
- GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
- Qwen2.5 Technical Report
- ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen3 Technical Report
- No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
- Output-Aware Rotation for INT2 KV-Cache Quantization
- OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data