Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914014853857280 |
|---|---|
| author | Girija, Sanjay Surendranath Kapoor, Shashank Arora, Lakshit Pradhan, Dipen Raj, Aman Shetgaonkar, Ankit |
| author_facet | Girija, Sanjay Surendranath Kapoor, Shashank Arora, Lakshit Pradhan, Dipen Raj, Aman Shetgaonkar, Ankit |
| contents | Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview of techniques for compressing LLMs to enable efficient inference in resource-constrained environments. We examine three primary approaches: Knowledge Distillation, Model Quantization, and Model Pruning. For each technique, we discuss the underlying principles, present different variants, and provide examples of successful applications. We also briefly discuss complementary techniques such as mixture-of-experts and early-exit strategies. Finally, we highlight promising future directions, aiming to provide a valuable resource for both researchers and practitioners seeking to optimize LLMs for edge deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02309 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques Girija, Sanjay Surendranath Kapoor, Shashank Arora, Lakshit Pradhan, Dipen Raj, Aman Shetgaonkar, Ankit Machine Learning Artificial Intelligence Computation and Language Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview of techniques for compressing LLMs to enable efficient inference in resource-constrained environments. We examine three primary approaches: Knowledge Distillation, Model Quantization, and Model Pruning. For each technique, we discuss the underlying principles, present different variants, and provide examples of successful applications. We also briefly discuss complementary techniques such as mixture-of-experts and early-exit strategies. Finally, we highlight promising future directions, aiming to provide a valuable resource for both researchers and practitioners seeking to optimize LLMs for edge deployment. |
| title | Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.02309 |