vLLM Office Hours #23 - Deep Dive Into the LLM Compressor - April 10, 2025

LLM Compressor is an easy-to-use library for optimizing models for deployment with vllm. We'll show you the power of the LLM Compressor via examples and easy pathways to get started with optimizing LLMs for fast and efficient vLLM inference. We'll also share the latest Llama 4 developments in vLLM! We also shared an update on Llama 4 Day 0 support in vLLM. Enjoy! Session slides: https://docs.google.com/presentation/d/1S2NnFqkbX4jLe84sY4ITSP4lOKGph5eN/ Join our bi-weekly vLLM Office Hours to learn about the latest features and updates: https://hubs.li/Q02Y5Pbh0