[vLLM Office Hours #33] Hybrid Models as First-Class Citizens in vLLM – September 25, 2025

Join us for our next vLLM Office Hours on September 25, 2025, at 2:00 PM EST! 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: Hybrid Models as First-Class Citizens in vLLM

We’ll kick things off with our regular vLLM project update from Michael Goin. Then, Thomas Parnell from IBM will lead a deep dive into hybrid models, covering:

1. What hybrid models are
2. Enabling hybrid models in vLLM v1
3. Mamba, Mamba2, and linear attention
4. Hybrid model performance in vLLM v0 vs. v1

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