QK-Wanda: Coupling Queries and Keys for Unstructured Pruning
cs.LG, cs.CL
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/vectozavr/qk-wanda
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
- The Llama 3 Herd of Models
- FASP: Fast and Accurate Structured Pruning of Large Language Models
- Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression
- Beware of Calibration Data for Pruning Large Language Models
- LLM-Pruner: On the Structural Pruning of Large Language Models
- Qwen2.5 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Attention Is All You Need
- RAP: KV-Cache Compression via RoPE-Aligned Pruning
- Symmetric Pruning of Large Language Models
- CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
- TinyLlama: An Open-Source Small Language Model
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