Production and MLOps Section 090

Batching and Concurrency

How to serve many users at once on the same hardware, instead of one at a time.

6 of 6 lessons published Three reading levels on every lesson

Start with “Dynamic batching”

Lessons in order

Work top to bottom. Each lesson assumes the one above it.

  1. Dynamic batching
  2. Continuous batching for LLMs
  3. Concurrency in a Python inference server
  4. Admission control and load shedding
  5. Deadlines, timeouts and retry storms
  6. Offline batch scoring