Code

Add prefix cache aware scheduling#768

Code

Merged

k8s-ci-robot merged 9 commits intokubernetes-sigs:mainkubernetes-sigs/gateway-api-inference-extension:mainfrom

liu-cong:prefix-cacheliu-cong/llm-instance-gateway:prefix-cacheCopy head branch name to clipboard

May 10, 2025

Commits

Commits on May 9, 2025

• Add prefix cache aware scheduling

  liu-cong

  committed
  f2b6457

  Copy full SHA for f2b6457

• Replace scheduler v2 with config v2

  liu-cong

  committed
  2bfc15a

  Copy full SHA for 2bfc15a

• Add score weight to XXScorerConfig

  liu-cong

  committed
  8a1f89f

  Copy full SHA for 8a1f89f

• Address comments

  liu-cong

  committed
  9447ad2

  Copy full SHA for 9447ad2

• Clean up

  liu-cong

  committed
  4b99fdd

  Copy full SHA for 4b99fdd

• Change to use container/list lib

  liu-cong

  committed
  3274a73

  Copy full SHA for 3274a73

• cleanup

  liu-cong

  committed
  81b24a5

  Copy full SHA for 81b24a5

• Add TODO

  liu-cong

  committed
  9769357

  Copy full SHA for 9769357

• make linter happy

  liu-cong

  committed
  47febd5

  Copy full SHA for 47febd5