The Serving Stack

Newsletter

Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.

Inference Notes

Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.

  1. No. 1Open

    vLLM matches DeepInfer on GB300 NVL72, plus GLM-5.3 and MiniMax day-0

    Hi, and welcome to the first Inference Notes, from The Serving Stack.