Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models

arXiv:2610.15781 · cs.LG, cs.AR, cs.CL · Submitted 2026-10-11 · Read on arXiv

cs.LG, cs.AR, cs.CL

Submitted: 2026-10-11

Updated: 2026-10-11

Terminology

• Pruning — 1× in this paper · explained in 4 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Weight Block Sparsity: Training, Compilation, and AI Engine Accelerators
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Accelerating Sparse Deep Neural Networks
• LLaMA: Open and Efficient Foundation Language Models
• Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT
• OPT: Open Pre-trained Transformer Language Models

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks