mlsanityData to 7 Oct 2026

EvoP: Robust LLM Inference via Evolutionary Pruning

arXiv 2502.14910 ↗First posted 19 Feb 2025cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, but their massive size and computational demands hinder their deployment in resource-constrained environments. Existing model pruning methods address this issue by removing redundant structures (e.g., elements, channels, layers) from the model. However, these methods employ a heuristic pruning strategy, which leads to suboptimal performance. Besides, they also ignore the data characteristics when pruning the model. To overcome these limitations, we propose EvoP, an evolutionary pruning framework for robust LLM inference. EvoP first presents a cluster-based calibration dataset sampling (CCDS) strategy for creating a more diverse calibration dataset. EvoP then introduces an evolutionary pruning pattern searching (EPPS) method to find the optimal pruning pattern. Compared to existing model pruning techniques, EvoP achieves the best performance while maintaining the best efficiency. Experiments across different LLMs and different downstream tasks validate the effectiveness of the proposed EvoP, making it a practical and scalable solution for deploying LLMs in real-world applications.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

32 of 39 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2016Pointer Sentinel Mixture Modelscited by 2,992
  9. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  10. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  11. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  12. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
20 more
  1. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  2. 2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 840
  3. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  5. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 776
  6. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  7. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  8. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 517
  9. 2024SliceGPT: Compress Large Language Models by Deleting Rows and Columnscited by 378
  10. 2020DeeBERT: Dynamic Early Exiting for Accelerating BERT Inferencecited by 322
  11. 2021Learning N:M Fine-grained Structured Sparse Neural Networks From Scratchcited by 177
  12. 2024SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blockscited by 96
  13. 2023EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelismcited by 69
  14. 2023Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMscited by 61
  15. 2020Contrastive Distillation on Intermediate Representations for Language Model Compressioncited by 57
  16. 2023SEENN: Towards Temporal Spiking Early-Exit Neural Networkscited by 39
  17. 2020Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domainscited by 33
  18. 2022Learning Best Combination for Efficient N:M Sparsitycited by 32
  19. 2020SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inferencecited by 30
  20. 2024CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsificationcited by 6

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inferencecited by 4
  2. 2025T'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimizationcited by 4