# StructPrune: Structured Global Pruning asymptotics with O(√N) GPU Memory

arXiv: https://arxiv.org/abs/2510.03246 · HTML: https://mlsanity.com/paper/2510.03246/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit](https://mlsanity.com/paper/1902.06015/) (2019)
- [Mean Field Analysis of Neural Networks: A Central Limit Theorem](https://mlsanity.com/paper/1808.09372/) (2018)
- [Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models](https://mlsanity.com/paper/2401.00625/) (2024)
- [The Curse of Depth in Large Language Models](https://mlsanity.com/paper/2502.05795/) (2025)
- [A Survey on Model Compression and Acceleration for Pretrained Language Models](https://mlsanity.com/paper/2202.07105/) (2022)
- [ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning](https://mlsanity.com/paper/2501.15316/) (2025)
- [Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression](https://mlsanity.com/paper/2504.05346/) (2025)
- [FASP: Fast and Accurate Structured Pruning of Large Language Models](https://mlsanity.com/paper/2501.09412/) (2025)
- [SPAP: Structured Pruning via Alternating Optimization and Penalty Methods](https://mlsanity.com/paper/2505.03373/) (2025)

## Built on by (most cited first, 1 of 1)

- [Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models](https://mlsanity.com/paper/2605.09008/) (2026)

## Abstract (arXiv)

Pruning is critical for scaling large language models (LLMs). Global pruning achieves strong performance but requires O(N) memory, which is infeasible for billion-parameter models. Local pruning reduces GPU memory usage to that of a single layer by pruning layers independently, but it neglects inter-layer dependencies and often leads to suboptimal performance in high-sparsity regimes. Unlike unstructured pruning, structured pruning produces regular sparsity patterns that align well with GPU kernels and library optimizations, making it more hardware-efficient. However, structured pruning typically relies on global pruning, since structured patterns are more prone to severe performance degradation under local optimization. To jointly achieve structured pruning and the memory efficiency of local pruning, we propose a divide-and-conquer strategy that decomposes the global pruning problem into coordinated subproblems across different modules, each of which fits within limited GPU memory. Building on this idea, we design STRUPRUNE, an ADMM-based framework that integrates structured sparsity into the pruning process, combining the memory efficiency of local pruning with the hardware compatibility of structured methods. We derive a closed-form analytical solution for structured pruning masks that provides an explicit rule for layer-wise sparsity allocation, and further develop an energy-based asymptotic framework yielding a softmax-form allocation scheme that simplifies optimization while adapting to heterogeneous layer importance. Experiments demonstrate that STRUPRUNE matches the perplexity of global structured pruning while reducing memory cost from O(N) to O(√N), enabling practical deployment at the billion-parameter scale.