Fast GPU Tests on PR

Workflow runs for Fast GPU Tests on PR

• Allow tensor parallelism and context parallelism in one ParallelConfig

  failed:
  Fast GPU Tests on PR#3889:Pull request#14725synchronizebyJingyaHuang
  whn09:tp-cp-compose

  Oct 14, 202649s
  More actions for workflow run 3889

• [feat] Tensor parallelism for MiniMax-H3

  failed:
  Fast GPU Tests on PR#3888:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 14, 202651m 41s
  More actions for workflow run 3888

• feat: implement cache_context for pab and fastercache.

  failed:
  Fast GPU Tests on PR#3887:Pull request#14900synchronizebysayakpaul
  refactor-pab-fastercache

  Oct 14, 202647m 21s
  More actions for workflow run 3887

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3886:Pull request#14865synchronizebyJingyaHuang
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 14, 202651m 13s
  More actions for workflow run 3886

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3885:Pull request#14865synchronizebyJingyaHuang
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 14, 202648m 43s
  More actions for workflow run 3885

• [feat] Tensor parallelism for MiniMax-H3

  failed:
  Fast GPU Tests on PR#3884:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 14, 202650m 16s
  More actions for workflow run 3884

• feat: implement cache_context for pab and fastercache.

  failed:
  Fast GPU Tests on PR#3883:Pull request#14900synchronizebysayakpaul
  refactor-pab-fastercache

  Oct 14, 202645m 28s
  More actions for workflow run 3883

• [feat] Tensor parallelism for MiniMax-H3

  failed:
  Fast GPU Tests on PR#3882:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 14, 202646m 33s
  More actions for workflow run 3882

• fix(models): restore temporarily offloaded weights after loading

  requires action with the application:
  Fast GPU Tests on PR#3881:Pull request#15026openedbyShenrui-Ma
  Shenrui-Ma:fix/restore-temporarily-offloaded-weights

  Oct 14, 2026Action required
  More actions for workflow run 3881

• tests: separate out ip adapter test state dict creation method

  failed:
  Fast GPU Tests on PR#3880:Pull request#14964synchronizebysayakpaul
  seperate-ip-adapter-state-dict

  Oct 14, 202645m 34s
  More actions for workflow run 3880

• [CI] Clean up test_modeling_common.py

  failed:
  Fast GPU Tests on PR#3879:Pull request#14988synchronizebyDN6
  remove-unet-mixin

  Oct 14, 202631s
  More actions for workflow run 3879

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3878:Pull request#14865synchronizebysayakpaul
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 14, 202645m 37s
  More actions for workflow run 3878

• [feat] Tensor parallelism for MiniMax-H3

  failed:
  Fast GPU Tests on PR#3877:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 13, 202646m 8s
  More actions for workflow run 3877

• [feat] Tensor parallelism for MiniMax-H3

  failed:
  Fast GPU Tests on PR#3876:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 13, 202646m 37s
  More actions for workflow run 3876

• [CI] Update test fetcher script

  failed:
  Fast GPU Tests on PR#3875:Pull request#14607synchronizebyDN6
  update-tests-fetcher-script

  Oct 13, 202647m 19s
  More actions for workflow run 3875

• [CI] Update test fetcher script

  cancelled:
  Fast GPU Tests on PR#3874:Pull request#14607synchronizebyDN6
  update-tests-fetcher-script

  Oct 13, 202650m 47s
  More actions for workflow run 3874

• [feat] Tensor parallelism for MiniMax-H3

  failed:
  Fast GPU Tests on PR#3873:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 13, 202649m 39s
  More actions for workflow run 3873

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3872:Pull request#14865synchronizebyJingyaHuang
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 12, 202651m 27s
  More actions for workflow run 3872

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3871:Pull request#14865synchronizebyJingyaHuang
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 12, 202649m 54s
  More actions for workflow run 3871

• [Quantization] Add support for Comfy-Kitchen / Comfy-Quants

  requires action with the application:
  Fast GPU Tests on PR#3870:Pull request#14747synchronizebyPrakshaaleJain
  PrakshaaleJain:feat/comfy-quant-support

  Oct 12, 2026Action required
  More actions for workflow run 3870

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3869:Pull request#14865synchronizebyJingyaHuang
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 12, 202645m 48s
  More actions for workflow run 3869

• [core] Tensor parallelism for Qwen-Image-2.1

  failed:
  Fast GPU Tests on PR#3868:Pull request#14865synchronizebyJingyaHuang
  JingyaHuang:add-qwen-image-21-tp-plan

  Oct 12, 202649m 44s
  More actions for workflow run 3868

• [Quantization] Add support for Comfy-Kitchen / Comfy-Quants

  requires action with the application:
  Fast GPU Tests on PR#3867:Pull request#14747synchronizebyPrakshaaleJain
  PrakshaaleJain:feat/comfy-quant-support

  Oct 11, 2026Action required
  More actions for workflow run 3867

• [feat] Tensor parallelism for MiniMax-H3

  completed successfully:
  Fast GPU Tests on PR#3866:Pull request#14609synchronizebyJingyaHuang
  JingyaHuang:add-h3-tp-support

  Oct 10, 202618m 21s
  More actions for workflow run 3866

• Fix missing cache contexts in Wan video-to-video

  requires action with the application:
  Fast GPU Tests on PR#3865:Pull request#14948synchronizebyfusheng-ji
  fusheng-ji:fix-12760-wan-v2v

  Oct 10, 2026Action required
  More actions for workflow run 3865