CALFA-KV: Joint Calibration and Fisher-Guided Anchors for 1-Bit KV Cache Compression
cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/XiancaiTian/CALFA-KV
Terminology
Sources
- Tailoring the Quantization Space for 1-Bit KV Cache Compression
- No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
- AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models
- OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
- Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms
- RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention
- RAQ-MLA: Role-Aware Quantization for Multi-Head Latent Attention Caches
- Output-Aware Rotation for INT2 KV-Cache Quantization
- FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference
- AnchorKV: Anchor-Residual KV Cache Compression
- Read What Matters: Query-Adaptive Quantization for KV Caches
- Training Verifiers to Solve Math Word Problems
- Instruction-Following Evaluation for Large Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis