Claude Code

Workflow runs for Claude Code

• [executorch][cuda] Compile quantized GEMM autotune configs in worker processes

  skipped:
  Claude Code#17337:Issue comment#23953 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17337

• [executorch][cuda] Trace a tuned quantized GEMM with only its picked config, timed in CUDA graphs

  skipped:
  Claude Code#17336:Issue comment#23952 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17336

• [executorch][cuda] Reuse PyTorch's access analysis of a repeated user Triton kernel call

  skipped:
  Claude Code#17335:Issue comment#23951 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17335

• [executorch][cuda] Write a weight storage the methods share only once

  skipped:
  Claude Code#17334:Issue comment#23950 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17334

• [executorch][cuda] Shorter autotune benchmark window and one compile pool for every split candidate

  skipped:
  Claude Code#17333:Issue comment#23949 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17333

• [executorch][cuda] Compile an autotuned quantized GEMM's configs in parallel before benchmarking them

  skipped:
  Claude Code#17332:Issue comment#23948 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17332

• Fold parameter-only subgraphs before XNNPACK partitioning

  skipped:
  Claude Code#17331:Issue comment#22391 (comment)createdbyjohn-rocky
  Oct 18, 20261s
  More actions for workflow run 17331

• [pytorch hash update] update the pinned pytorch hash

  skipped:
  Claude Code#17330:Issue comment#10955 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20268s
  More actions for workflow run 17330

• [pytorch hash update] update the pinned pytorch hash

  skipped:
  Claude Code#17329:Issue comment#10955 (comment)createdbypytorchbot
  Oct 18, 20261s
  More actions for workflow run 17329

• Qualcomm: 16a16w quantization is much less accurate than 16a8w

  skipped:
  Claude Code#17328:Issue comment#23108 (comment)createdbymsluszniak
  Oct 18, 20262s
  More actions for workflow run 17328

• Qualcomm: 16a16w quantization is much less accurate than 16a8w

  skipped:
  Claude Code#17327:Issue comment#23108 (comment)createdbyqti-horodnic
  Oct 17, 20261s
  More actions for workflow run 17327

• Qualcomm AI Engine Direct - Support QAT for concat observer

  skipped:
  Claude Code#17326:Issue comment#23347 (comment)createdbyshewu-quic
  Oct 17, 20261s
  More actions for workflow run 17326

• Do not delegate CoreML integer mm with a constant weight

  skipped:
  Claude Code#17325:Issue comment#23689 (comment)createdbyhemanth1999k
  Oct 17, 20262s
  More actions for workflow run 17325

• Do not delegate CoreML reflect/replicate pads beyond the last two dims

  skipped:
  Claude Code#17324:Issue comment#23687 (comment)createdbyhemanth1999k
  Oct 17, 20261s
  More actions for workflow run 17324

• [PyBindings] Add zero-copy DLPack interchange

  skipped:
  Claude Code#17323:Issue comment#23090 (comment)createdbymeta-codesync[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17323

• [native] Add an ExecuTorch Native docs page

  skipped:
  Claude Code#17322:Issue comment#23946 (comment)createdbypytorch-bot[bot]Bot
  Oct 17, 2026Skipped
  More actions for workflow run 17322

• [native] Add a single ExecuTorch Native README

  skipped:
  Claude Code#17321:Issue comment#23945 (comment)createdbypytorch-bot[bot]Bot
  Oct 17, 20262s
  More actions for workflow run 17321

• [pytorch hash update] update the pinned pytorch hash

  skipped:
  Claude Code#17320:Issue comment#10955 (comment)createdbypytorch-bot[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17320

• [pytorch hash update] update the pinned pytorch hash

  skipped:
  Claude Code#17319:Issue comment#10955 (comment)createdbypytorchbot
  Oct 17, 20261s
  More actions for workflow run 17319

• Invalidate Android Module outputs once their memory is reused

  skipped:
  Claude Code#17318:Issue comment#23445 (comment)createdbymeta-cla[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17318

• Add the WebGPU Playground (experimental) (#23944)

  skipped:
  Claude Code#17317:Issue comment#23944 (comment)createdbymeta-codesync[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17317

• Add the WebGPU Playground (experimental) (#23944)

  skipped:
  Claude Code#17316:Issue comment#23944 (comment)createdbypytorch-bot[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17316

• fix(cortex-m): don't replace channels-first conv with channels-last kernel

  skipped:
  Claude Code#17315:Issue comment#23943 (comment)createdbylinux-foundation-easycla[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17315

• fix(cortex-m): don't replace channels-first conv with channels-last kernel

  skipped:
  Claude Code#17314:Issue comment#23943 (comment)createdbymeta-cla[bot]Bot
  Oct 17, 20268s
  More actions for workflow run 17314

• fix(cortex-m): don't replace channels-first conv with channels-last kernel

  skipped:
  Claude Code#17313:Issue comment#23943 (comment)createdbypytorch-bot[bot]Bot
  Oct 17, 20261s
  More actions for workflow run 17313