Guides
Welcome to the LLM Compressor guides section! Here you'll find comprehensive documentation covering key components and concepts of LLM Compressor. These guides will help you understand the various compression options available, how to apply them effectively, and how to deploy your optimized models for maximum performance.
Key Guides
-
Compression Schemes
Explore the available compression schemes for Quantization and Pruning to determine which is best for your use case.
-
Saving Models
Learn the enhanced ways to save your compressed models with the library's extended
save_pretrainedfunctionality for compatibility with vLLM deployment.