All pull requests

Pull requests

• [Bugfix] Classify Nemotron Super VL capabilities

  tests
  #1199·JasonDong-ORCL opened Oct 2, 2026·1 of 3 tasks·

  ·
  1

• [Docs] Refresh OME workflows and examples

  ciconfigdocumentationtests
  #1191·slin1237 opened Oct 1, 2026Collaborator·

  ·
  2

• Bump k8s.io/code-generator from 0.33.1 to 0.37.1 in /hack/internal/tools

  dependencies
  #1185·dependabot[bot] opened Sep 30, 2026Bot·

  ·
  2

• Bump sigs.k8s.io/controller-tools from 0.18.0 to 0.22.0 in /hack/internal/tools

  dependencies
  #1106·dependabot[bot] opened Sep 26, 2026Bot·

  ·
  3

• [Bugfix] scheduler: defer gang pin until hard spread filtering

  controllerdocumentationhelmtests
  #867·robin-inferact opened Sep 8, 2026Contributor·2 of 3 tasks·

  ·
  1

• [Core] Report Alfred node health policy

  configdocumentationoeptests
  #865·pallasathena92 opened Sep 7, 2026Collaborator·

  ·
  7

• [Core] Model Alfred node health states

  documentationoeptests
  #858·pallasathena92 opened Sep 7, 2026Collaborator·

  ·
  7

• Prioritize serving-demand model downloads

  apiconfigcontrollercrddocumentationhelmmodel-agenttests
  #838·gsgvijay opened Sep 1, 2026·

  ·
  35

• [Core] Refresh Alfred before early decisions

  documentationoeptests
  #828·pallasathena92 opened Sep 1, 2026Collaborator·

  ·
  21

• [Core] Keep Alfred execution fail closed

  configcontrollerdocumentationhelmoeptests
  #827·pallasathena92 opened Sep 1, 2026Collaborator·

  ·
  15

• [Core] Add modelpack:// storage via llmman serve

  apibenchmarkcontrollerdocumentationmodel-agentome-agenttestswebhook
  #797·ericcurtin opened Aug 30, 2026·

  ·
  34

• Optimize multipart model downloads with direct writes

  helmmodel-agentstoragetests
  #791·fredericsun opened Aug 26, 2026Collaborator·3 tasks done·

  ·
  14

• [Core] add stage:// storage protocol for shared-storage models

  helmmodel-agentmodelstestswebhook
  #788·weetime opened Aug 24, 2026Contributor·2 of 3 tasks·

  ·
  1

  25

• Bump istio.io/api from 1.19.4 to 1.31.0

  dependencies
  #764·dependabot[bot] opened Aug 15, 2026Bot·

  ·
  3

• [Runtime] Add SEA-LION v4 32B source runtime

  configmodelsruntime
  #675·ankrovv opened Jul 17, 2026·3 tasks done·

  ·
  3

• Update GPT-OSS model-import runtimes

  configruntime
  #636·ankrovv opened Jun 24, 2026·3 tasks·

  ·

• [Runtime] GLM 5.2 FP8 multi node runtimes

  configmodelsruntime
  #634·YouNeedCryDear opened Jun 23, 2026Collaborator·3 tasks·

  ·

• Add Kimi K2.5 generation vLLM runtime and K2.6/K2.7-Code models

  configmodelsruntime
  #633·Juno13340 opened Jun 22, 2026·1 of 3 tasks·

  ·
  9

• [Runtime] DeepSeek v4 pro multi node runtimes

  configruntime
  #631·YouNeedCryDear opened Jun 17, 2026Collaborator·3 tasks·

  ·
  4

• [Runtime] Add Qwen3-32B, Qwen3-Embedding-8B, and Qwen3Guard-Gen-8B vLLM runtimes

  configmodelsruntime
  #628·Juno13340 opened Jun 9, 2026·1 of 3 tasks·

  ·
  7

• [Bugfix] update-node-ready-logic

  configcontrollerdocumentationhelmmodel-agentstoragetests
  #615·ankrovv opened May 19, 2026·3 tasks done·

  ·
  1

• [Core] Add RBGStrategy workload strategy following OEP-0006

  autoscalingconfigcontrollerdependencieshelminferenceservicerbactests
  #614·diw-zw opened May 18, 2026·3 tasks·

  ·
  1

• Add InferenceService lifecycle state

  apiconfigcontrollercrdhelminferenceservicetests
  #612·kartikkhurana1898 opened May 14, 2026·

  ·

• [Runtime] Add NVIDIA-Nemotron-3-Super-120B-A12B-FP8 runtime

  configmodelsruntime
  #610·TJ5 opened May 12, 2026·3 tasks done·

  ·
  8

• [Runtime] Add Qwen 3.6 35B A3B 1M context runtime

  configmodelsruntime
  #609·YouNeedCryDear opened May 12, 2026Collaborator·3 tasks·

  ·