Labeler

Workflow runs for Labeler

• [ET-VK] Cooperative-matrix kernels for 4-bit linear on Intel Xe2 and NVIDIA

  completed successfully:
  Labeler#20188:Pull request#24000synchronizebyxuyanwen2012
  Oct 22, 202613s
  More actions for workflow run 20188

• Allow overriding the QNN SDK version via buck config (#24102)

  completed successfully:
  Labeler#20187:Pull request#24102openedbybillmguo
  Oct 22, 202614s
  More actions for workflow run 20187

• Make removing an Apple log sink safe from its dealloc or deinit

  completed successfully:
  Labeler#20186:Pull request#24101openedbyshoumikhin
  Oct 22, 202611s
  More actions for workflow run 20186

• Support int16 in vision quantized_layer_norm (#24094)

  completed successfully:
  Labeler#20185:Pull request#24094synchronizebymvartani-meta
  Oct 22, 202613s
  More actions for workflow run 20185

• Support int16 in generic quantized_layer_norm (#24093)

  completed successfully:
  Labeler#20184:Pull request#24093synchronizebymvartani-meta
  Oct 22, 202614s
  More actions for workflow run 20184

• Generate ring masks directly as packed bits (#24089)

  completed successfully:
  Labeler#20183:Pull request#24089synchronizebyThomasJannaud
  Oct 22, 202614s
  More actions for workflow run 20183

• Support int16 in HiFi quantized_layer_norm (#24091)

  completed successfully:
  Labeler#20182:Pull request#24091synchronizebymvartani-meta
  Oct 22, 202614s
  More actions for workflow run 20182

• Fix llama_qnn Buck target import failures

  completed successfully:
  Labeler#20181:Pull request#24100openedbybillmguo
  Oct 22, 202613s
  More actions for workflow run 20181

• Fix Windows CUDA wheel conda bootstrap

  completed successfully:
  Labeler#20180:Pull request#24099openedbyGasoonjia
  Oct 22, 202614s
  More actions for workflow run 20180

• [executorch][cuda] Check FQN weight coverage without AOTI's per-buffer warnings

  completed successfully:
  Labeler#20179:Pull request#24052synchronizebyGasoonjia
  Oct 22, 202615s
  More actions for workflow run 20179

• [executorch][cuda] Check FQN weight coverage without AOTI's per-buffer warnings

  completed successfully:
  Labeler#20178:Pull request#24052synchronizebyGasoonjia
  Oct 22, 202610s
  More actions for workflow run 20178

• [executorch][muse] Fix the DFlash final-block draft counts test

  completed successfully:
  Labeler#20177:Pull request#24050synchronizebyGasoonjia
  Oct 22, 202614s
  More actions for workflow run 20177

• Drop the unused LLVM download from setup-qnn-deps.sh

  completed successfully:
  Labeler#20176:Pull request#24098openedbyshoumikhin
  Oct 22, 202611s
  More actions for workflow run 20176

• Find the tuned INT4 kernel's def under its module-level name too

  completed successfully:
  Labeler#20175:Pull request#24097openedbybobrenjc93
  Oct 22, 202613s
  More actions for workflow run 20175

• [executorch][cuda] Find the tuned INT4 kernel's def under its module-level name too

  completed successfully:
  Labeler#20174:Pull request#24096openedbybobrenjc93
  Oct 22, 202613s
  More actions for workflow run 20174

• CUDA wheel: check every dependency, and give torch_cpu_library targets torch's compile settings back

  completed successfully:
  Labeler#20173:Pull request#24087synchronizebyshoumikhin
  Oct 22, 202613s
  More actions for workflow run 20173

• Support int16 in vision quantized_layer_norm (#24094)

  completed successfully:
  Labeler#20172:Pull request#24094openedbymvartani-meta
  Oct 22, 202614s
  More actions for workflow run 20172

• Support int16 in generic quantized_layer_norm (#24093)

  completed successfully:
  Labeler#20171:Pull request#24093openedbymvartani-meta
  Oct 22, 202613s
  More actions for workflow run 20171

• Give test-qnn-python-imports-linux 30 minutes instead of 15

  completed successfully:
  Labeler#20170:Pull request#24092openedbyshoumikhin
  Oct 22, 202612s
  More actions for workflow run 20170

• Support int16 in HiFi quantized_layer_norm (#24091)

  completed successfully:
  Labeler#20169:Pull request#24091openedbymvartani-meta
  Oct 22, 202614s
  More actions for workflow run 20169

• Keep the caller's numpy when setting up the Core ML backend

  completed successfully:
  Labeler#20168:Pull request#24090openedbyshoumikhin
  Oct 22, 202611s
  More actions for workflow run 20168

• Fix device placement of constants, shared inputs and delegate outputs

  completed successfully:
  Labeler#20167:Pull request#24088synchronizebyshoumikhin
  Oct 22, 202612s
  More actions for workflow run 20167

• Generate ring masks directly as packed bits (#24089)

  completed successfully:
  Labeler#20166:Pull request#24089synchronizebyThomasJannaud
  Oct 22, 202612s
  More actions for workflow run 20166

• Add opt-in LTO for portable executor (#24001)

  completed successfully:
  Labeler#20165:Pull request#24001synchronizebyivayloen
  Oct 22, 202611s
  More actions for workflow run 20165

• Generate ring masks directly as packed bits (#24089)

  completed successfully:
  Labeler#20164:Pull request#24089openedbyThomasJannaud
  Oct 22, 202614s
  More actions for workflow run 20164