GPU Examples

Workflow runs for GPU Examples

• Pack float and INT4 QKV projections with deferred weight binding (#754)

  failed:
  GPU Examples#474:Commit858eadfpushedbytitaiwangms
  main

  Nov 6, 20261d 0h 0m 2s
  More actions for workflow run 474

• GPU Examples

  cancelled:
  GPU Examples#473:Manually runbyeserscor
  main

  Nov 6, 20264h 20m 29s
  More actions for workflow run 473

• Improve new-model validation skills from LFM3 lessons (#811)

  cancelled:
  GPU Examples#472:Commit1100038pushedbyjustinchuby
  main

  Nov 5, 202614h 39m 36s
  More actions for workflow run 472

• Clarify SKILL.md for Microsoft-managed machines (#812)

  failed:
  GPU Examples#471:Commit030db17pushedbyjustinchuby
  main

  Nov 4, 20261d 0h 0m 2s
  More actions for workflow run 471

• GPU Examples

  cancelled:
  GPU Examples#470:Manually runbyeserscor
  main

  Nov 4, 20266h 35m 2s
  More actions for workflow run 470

• Support per-channel quantized export and configurable MatMulNBits acc…

  failed:
  GPU Examples#469:Commitc0d6a20pushedbyneilmsft
  main

  Nov 2, 20261d 0h 0m 3s
  More actions for workflow run 469

• Fix isolated Python setup and rename the ADO build definition (#809)

  cancelled:
  GPU Examples#468:Commit57dadb4pushedbyjustinchuby
  main

  Nov 2, 20262h 15m 12s
  More actions for workflow run 468

• Isolate A10 CI Python dependencies to fix PEP 668 failures (#806)

  cancelled:
  GPU Examples#467:Commit458cbdfpushedbyeserscor
  main

  Nov 2, 20265h 49m 15s
  More actions for workflow run 467

• Publish mobius releases through ESRP (#808)

  failed:
  GPU Examples#466:Commit7f61c0dpushedbyjustinchuby
  main

  Oct 29, 20261d 0h 0m 2s
  More actions for workflow run 466

• Add multi-component export support for CLM and KEV (#749)

  failed:
  GPU Examples#465:Commit0cc842fpushedbyapsonawane
  main

  Oct 27, 20261d 0h 0m 2s
  More actions for workflow run 465

• Fix CI dependency resolution for pinned Transformers and VibeVoice (#…

  failed:
  GPU Examples#464:Commit2e5508fpushedbytitaiwangms
  main

  Oct 26, 20261d 0h 0m 1s
  More actions for workflow run 464

• Fix INT3 deferred-weight tests for parallel ONNX saves (#782)

  failed:
  GPU Examples#463:Commitd69efe0pushedbytitaiwangms
  main

  Oct 20, 20261d 0h 0m 2s
  More actions for workflow run 463

• Fix selected precision in golden reference generation (#781)

  cancelled:
  GPU Examples#462:Commit9408770pushedbytitaiwangms
  main

  Oct 20, 20263h 21m 11s
  More actions for workflow run 462

• Fix Gemma 4 OpenVINO NPU graph export (#766)

  cancelled:
  GPU Examples#461:Commit243b8f3pushedbyxiaoyu-work
  main

  Oct 19, 202622h 7m 59s
  More actions for workflow run 461

• Enable standard-ONNX Qwen3.8 Flash-Next export (#755)

  cancelled:
  GPU Examples#460:Commitfd8b2fdpushedbytitaiwangms
  main

  Oct 19, 20264h 51m 37s
  More actions for workflow run 460

• Add projection-specific INT2/INT3/INT4/INT8 QMoE export (#764)

  failed:
  GPU Examples#459:Commitb1e9c8epushedbytitaiwangms
  main

  Oct 15, 20261d 0h 0m 2s
  More actions for workflow run 459

• Qualify complete Qwen3.8-27B standard-only VLM export (#758)

  failed:
  GPU Examples#458:Commitd734346pushedbytitaiwangms
  main

  Oct 13, 20261d 0h 0m 3s
  More actions for workflow run 458

• Support quantized Gemma 4 per-layer input projections (#762)

  failed:
  GPU Examples#457:Commit88f7d04pushedbyxiaoyu-work
  main

  Oct 9, 20261d 0h 0m 1s
  More actions for workflow run 457

• Preserve full Gemma4 Unified audio in exported preprocessing (#759)

  failed:
  GPU Examples#456:Commit26a712bpushedbytitaiwangms
  main

  Oct 7, 20261d 0h 7m 35s
  More actions for workflow run 456

• Fix Gemma 4 audio processor operation (#752)

  failed:
  GPU Examples#455:Commitdc17984pushedbyxiaoyu-work
  main

  Oct 3, 20261d 0h 0m 2s
  More actions for workflow run 455

• Adding Nemotron 3 Diarization ONNX Model Support (#748)

  failed:
  GPU Examples#454:Commitc2fde93pushedbythemason2011
  main

  Sep 30, 20261d 0h 0m 2s
  More actions for workflow run 454

• Support mixed-width QMoE export (#744)

  failed:
  GPU Examples#453:Commit88fd6a1pushedbytitaiwangms
  main

  Sep 28, 20261d 0h 0m 2s
  More actions for workflow run 453

• Describe cross-component tied weights (#747)

  failed:
  GPU Examples#452:Commit6bd398dpushedbyxiaoyu-work
  main

  Sep 26, 20261d 0h 0m 2s
  More actions for workflow run 452

• Qualify Olive INT2 checkpoint export (#740)

  failed:
  GPU Examples#451:Commit783e03bpushedbytitaiwangms
  main

  Sep 22, 20261d 0h 0m 1s
  More actions for workflow run 451

• ort_genai: native processor configs for gemma-4-12B unified (#391)

  failed:
  GPU Examples#450:Commit6b27a3fpushedbytitaiwangms
  main

  Sep 18, 20261d 0h 0m 3s
  More actions for workflow run 450