[vLLM Office Hours #47] LLM Compressor Update – April 16, 2026

Welcome to vLLM office hours! These bi-weekly sessions are your chance to stay current with the vLLM ecosystem, ask questions, and hear directly from contributors and power users.

This week’s special topic: LLM Compressor Update: Distributed Data Parallel (DDP) and Enhanced Offloading Support

We’ll kick off with the latest vLLM project updates by vLLM Core Committer Michael Goin, followed by a session with Red Hat AI’s Model Optimization team on what’s new with LLM Compressor. If you are new to LLM Compressor, it’s an open source library part of the vLLM project for accurately quantizing LLMs for faster and more efficient inference. Check it out here: https://github.com/vllm-project/llm-compressor. The team will share recent features and how the community can benefit, followed by an open discussion and Q&A.

Want to join the discussion live on Google Meet? Get a calendar invite by filling out this form: https://red.ht/office-hours