LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/mscheong01/LoopVQ
Terminology
Sources
- Program Synthesis with Large Language Models
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- Evaluating Large Language Models Trained on Code
- Tailoring the Quantization Space for 1-Bit KV Cache Compression
- Training Verifiers to Solve Math Word Problems
- Universal Transformers
- Extreme Compression of Large Language Models via Additive Quantization
- LoopQ: Quantization for Looped Language Models
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- The Llama 3 Herd of Models
- Distilling the Knowledge in a Neural Network
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit Residuals
- Loopy: Low-Bit Quantization Framework for Looped Language Models
- Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates
- LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers
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