[vLLM Office Hours #30] Hybrid Memory Allocator Architecture in vLLM

Join us for our next vLLM Office Hours on August 11, 2025, at 2:00pm EST! These bi-weekly sessions are your chance to stay up to date on the latest in the vLLM ecosystem, ask questions, and hear directly from contributors and power users.

This week’s special topic: Hybrid Memory Allocator Architecture in vLLM

We’ll start with our bi-weekly vLLM project update by Michael Goin. After that, join Chen Zhang, as she walks through vLLM’s new hybrid memory allocator architecture. She’ll cover:

1. The new trends of different attention machinisms
2. How hybrid memory allocator is integrated in vLLM
3. Future plans for the hybrid memory allocator

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