llm-pruning

Tag

Cards List
#llm-pruning

Building a Nested LADDER for LLM Unstructured Post-Training Pruning

arXiv cs.LG ↗ · 2026-10-22 Cached

论文提出 LADDER(Layer-Wise Allocation via Damage-Driven Evaluation and Refinement),一种针对大语言模型的非均匀后训练剪枝方法,通过逐层评估最小化每移除参数的性能损失,生成嵌套掩码轨迹,在 70% 以上高稀疏度下表现显著优于基线。

0 favorites 0 likes
#llm-pruning

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

Hugging Face Blog ↗ · 2026-09-21 Cached

The paper presents a physics-inspired approach to pruning LLM blocks by modeling block removal as a constrained binary optimization problem mapped to an Ising glass, achieving significant compression gains without benchmarking each configuration.

0 favorites 0 likes
#llm-pruning

Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

arXiv cs.CL ↗ · 2026-08-14 Cached

This paper introduces Sniper, a two-stage structured pruning framework for LLMs that uses binary knapsack optimization to unify depth and width pruning, achieving near-exact compression ratio adherence and improved performance retention across multiple architectures.

0 favorites 0 likes
#llm-pruning

When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning

arXiv cs.AI ↗ · 2026-08-05 Cached

This paper analyzes why compression statistics for LLM pruning can be reproducible yet select suboptimal endpoints, introducing information boundaries and observation fibers to model the gap. It proposes group-resolved and model-specific mask selection methods that improve worst-group perplexity across dense LLMs and OLMoE.

0 favorites 0 likes
#llm-pruning

PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning

arXiv cs.CL ↗ · 2026-07-09 Cached

PALS adjusts per-layer sparsity ratios for LLM pruning based on the 99th percentile of activation magnitudes, achieving significant perplexity improvements on LLaMA-2-7B compared to uniform sparsity, with negligible added cost.

0 favorites 0 likes
#llm-pruning

Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT

arXiv cs.CL ↗ · 2026-06-26 Cached

This paper presents a cascaded multi-granularity pruning framework for deploying LLMs on Industrial IoT edge devices, achieving up to 13.8x compression with minimal accuracy loss on MHA+GELU architectures while exposing a collapse on GQA+SwiGLU designs.

0 favorites 0 likes
#llm-pruning

Small LLMs: Pruning vs. Training from Scratch

arXiv cs.LG ↗ · 2026-06-15 Cached

This paper empirically compares pruning vs. training small language models from scratch, finding that pruning provides a strong advantage under limited token budgets but that the advantage diminishes as training scales, especially with coarse pruning.

0 favorites 0 likes
← Back to home

Submit Feedback