Red Hat live session: vLLM core maintainer breaks down inference performance knobs

AccBalanced · x · 2026-11-18

Red Hat AI is hosting a live session on Nov 18, 2pm ET on mastering AI inference performance at scale, featuring vLLM core maintainer Tyler Michael Smith and Yuchen Fama. Topics: parallelism, scheduling, KV cache offloading, and prefill/decode disaggregation — and when each optimization actually pays off.

Original post →

More from Infra

Infra channel →