Lessons

1Put admission before the expensive work25 min read

Design admission limits using token and time budgets.

  • →Design admission limits using token and time budgets
  • →Design fair admission for unequal request sizes
Read lesson
2Make cache reuse measurable and safe25 min read

Evaluate prefix caching without assuming universal speedups.

  • →Evaluate prefix caching without assuming universal speedups
Read lesson
3Scale using queue behavior and warm capacity25 min read

Choose scaling signals that predict user-visible overload.

  • →Choose scaling signals that predict user-visible overload
Read lesson
4Release a model without losing the escape route25 min read

Specify a model rollout and rollback contract.

  • →Specify a model rollout and rollback contract
  • →Specify rollback checks for a model release
Read lesson

Skills in this course

  1. 01Design admission limits using token and time budgetsDesign admission limits using token and time budgets.
  2. 02Evaluate prefix caching without assuming universal speedupsEvaluate prefix caching without assuming universal speedups.
  3. 03Choose scaling signals that predict user-visible overloadChoose scaling signals that predict user-visible overload.
  4. 04Specify a model rollout and rollback contractSpecify a model rollout and rollback contract.
  5. 05Design fair admission for unequal request sizesDesign fair admission for unequal request sizes.
  6. 06Specify rollback checks for a model releaseSpecify rollback checks for a model release.