QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching
cs.LG, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-30
Code: https://github.com/meituan-longcat/LongCat-2.0
Terminology
Sources
- PIQA: Reasoning about Physical Commonsense in Natural Language
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- DeepSeek-V3 Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
- PolarQuant: Quantizing KV Caches with Polar Transformation
- Measuring Mathematical Problem Solving With the MATH Dataset
- OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
- Kimi K2: Open Agentic Intelligence
- Kimi Linear: An Expressive, Efficient Attention Architecture
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
- Muon is Scalable for LLM Training
- Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
- LongCat-Flash Technical Report
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks