All pull requests

Pull requests

• fix: align MultiRoleInference webhook validation with child InferenceSets

  #2447·andyzhangx opened Oct 20, 2026Collaborator·1 task done·

  ·
  13

• feat: separate InferenceSet node selector from workload labelSelector

  #2444·zhuangqh opened Oct 19, 2026Collaborator·1 task done·

  ·

• chore: bump lmcache to 0.5.6

  #2435·katsugtgz opened Oct 17, 2026·

  ·
  2

• fix: preserve conflict status when loading an existing index

  #2434·spicysharkco opened Oct 17, 2026·1 task done·

  ·

• chore: bump python from 3.12-slim-bookworm to 3.15-slim-bookworm in /docker/presets/models/tfs

  dependenciesdocker
  #2432·dependabot[bot] opened Oct 16, 2026Bot·

  ·

• feat: add basic CPU inference support

  #2431·andyzhangx opened Oct 16, 2026Collaborator·

  ·
  125

• fix: release unreferenced model registry entries

  #2430·zhuangqh opened Oct 16, 2026Collaborator·1 task·

  ·
  6

• feat: surface Karpenter node provisioning failures in Workspace and InferenceSet status

  #2429·rambohe-ch opened Oct 15, 2026Collaborator·1 task done·

  ·
  5

• fix: apply custom inference template updates to the workspace StatefulSet

  #2416·jackiectl2 opened Oct 10, 2026·1 task done·

  ·
  1

• chore: bump shell-quote from 1.10.0 to 1.12.0 in /website

  dependenciesjavascript
  #2403·dependabot[bot] opened Oct 6, 2026Bot·

  ·

• chore: bump react from 19.2.8 to 19.3.0 in /website

  dependenciesjavascript
  #2402·dependabot[bot] opened Oct 6, 2026Bot·

  ·

• docs: revise distributed cache attachment API

  #2375·hasethuraman opened Sep 27, 2026Contributor·1 task·

  ·
  2

• feat: add Envoy ext_proc streaming output-guardrail PoC

  #2374·ItsRoy69 opened Sep 25, 2026·1 task done·

  ·
  1

• fix: inject RAGEngine remote embedding config with correct env var names

  #2366·pujitha24 opened Sep 20, 2026·1 task done·

  ·
  1

• feat: migrate KV cache offloading to use LMCacheMPConnector

  #2364·zhehli688 opened Sep 19, 2026Collaborator·2 of 3 tasks·

  ·
  1

  5

• fix: stop overriding vLLM's dynamic gpu-memory-utilization default

  #2339·pujitha24 opened Sep 11, 2026·1 task done·

  ·
  1

  1

• ci: verify generated RBAC relationships

  #2313·lokesh0186 opened Sep 1, 2026·1 task·

  ·
  1

• chore: update httpx requirement from <1.0,>=0.27.0 to >=0.28.1,<1.0 in /presets/workspace/dependencies

  dependenciespython
  #2300·dependabot[bot] opened Aug 24, 2026Bot·

  ·
  1

• chore: bump httpx from 0.27.0 to 0.28.1 in /presets/ragengine

  dependenciespython
  #2299·dependabot[bot] opened Aug 24, 2026Bot·

  ·
  2

• chore: bump aiorwlock from 1.5.0 to 1.5.1 in /presets/ragengine

  dependenciespython
  #2298·dependabot[bot] opened Aug 24, 2026Bot·

  ·
  2

• chore: bump aquasecurity/trivy-action from 0.35.0 to 0.36.0

  dependenciesgithub_actions
  #2297·dependabot[bot] opened Aug 24, 2026Bot·

  ·

• feat: expose terminationGracePeriodSeconds on InferenceSet and Workspace

  #2271·Antrikshgwal opened Aug 11, 2026·1 task done·

  ·
  1

• [WIP] chore: switch default registry to oss/v2/kaito

  #2261·andyzhangx opened Aug 6, 2026Collaborator·

  ·
  6

• feat: pluggable model cache framework

  #2190·hasethuraman opened Jul 15, 2026Contributor·

  ·
  89

• feat: distributed cache integration

  #2169·croomes opened Jun 30, 2026Contributor·1 task done·

  ·
  58