Claude Code

Workflow runs for Claude Code

• Quacomm AI Engine Direct - Bump QNN SDK version from 2.50 to 2.51

  skipped:
  Claude Code#17388:Issue comment#23918 (comment)createdbymeta-codesync[bot]Bot
  Oct 19, 202611s
  More actions for workflow run 17388

• Rename executorch cmake target to prim_ops_lib

  skipped:
  Claude Code#17387:Issue comment#23177 (comment)createdbyTejasweeSulekh
  Oct 19, 20261s
  More actions for workflow run 17387

• [executorch][muse] Run the CUDA DFlash drafter in CUDA graphs

  skipped:
  Claude Code#17386:Issue comment#23985 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17386

• [executorch][muse] Verify CUDA DFlash drafts on device under any sampling

  skipped:
  Claude Code#17385:Issue comment#23984 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17385

• [executorch][muse] Draft CUDA DFlash decode from pending tokens

  skipped:
  Claude Code#17384:Issue comment#23983 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17384

• [executorch][muse] Copy only committed DFlash hidden rows to host

  skipped:
  Claude Code#17383:Issue comment#23982 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17383

• [executorch][muse] Add cuda dflash executor

  skipped:
  Claude Code#17382:Issue comment#23981 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17382

• [executorch][muse] Export packed DFlash drafts for CUDA batching

  skipped:
  Claude Code#17381:Issue comment#23980 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17381

• [executorch][cuda] Expose raw packed steps on CudaExecutor

  skipped:
  Claude Code#17380:Issue comment#23979 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17380

• [executorch][cuda] Run packed noncausal DFlash draft steps on the cell cache

  skipped:
  Claude Code#17379:Issue comment#23978 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17379

• Reject execute() after a refused set_inputs() and get_outputs() without a successful execute()

  skipped:
  Claude Code#17378:Issue comment#23977 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17378

• [cuda] Skip the unstartable-pool worker test on ROCm

  skipped:
  Claude Code#17377:Issue comment#23976 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17377

• Quacomm AI Engine Direct - Bump QNN SDK version from 2.50 to 2.51

  skipped:
  Claude Code#17376:Issue comment#23918 (comment)createdbywinskuo-quic
  Oct 19, 20261s
  More actions for workflow run 17376

• Fix test_silence_skip_resets_on_reset hang: ET log sink deadlocks on GIL (#23975)

  skipped:
  Claude Code#17375:Issue comment#23975 (comment)createdbymeta-codesync[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17375

• Fix test_silence_skip_resets_on_reset hang: ET log sink deadlocks on GIL (#23975)

  skipped:
  Claude Code#17374:Issue comment#23975 (comment)createdbylinux-foundation-easycla[bot]Bot
  Oct 19, 20261s
  More actions for workflow run 17374

• Fix test_silence_skip_resets_on_reset hang: ET log sink deadlocks on GIL (#23975)

  skipped:
  Claude Code#17373:Issue comment#23975 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20262s
  More actions for workflow run 17373

• [pytorch hash update] update the pinned pytorch hash

  skipped:
  Claude Code#17372:Issue comment#10955 (comment)createdbypytorch-bot[bot]Bot
  Oct 19, 20262s
  More actions for workflow run 17372

• [pytorch hash update] update the pinned pytorch hash

  skipped:
  Claude Code#17371:Issue comment#10955 (comment)createdbypytorchbot
  Oct 19, 20261s
  More actions for workflow run 17371

• [executorch][muse] Serve Muse Glimmer CUDA batching on a batched-sequence cache

  skipped:
  Claude Code#17370:Issue comment#23974 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17370

• [executorch][cuda] Lower off-graph KV to the batched-sequence layout

  skipped:
  Claude Code#17369:Issue comment#23973 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17369

• [executorch][cuda] Add a batched-sequence CUDA KV cache

  skipped:
  Claude Code#17368:Issue comment#23972 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17368

• [executorch][cuda] Add a length-aware Triton SDPA over per-sequence KV columns

  skipped:
  Claude Code#17367:Issue comment#23971 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17367

• [executorch][muse] Accept images in CUDA DFlash batching

  skipped:
  Claude Code#17366:Issue comment#23970 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17366

• [executorch][muse] Serve images on CUDA batching

  skipped:
  Claude Code#17365:Issue comment#23969 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20261s
  More actions for workflow run 17365

• [executorch][muse] Export vision with the CUDA batching contract

  skipped:
  Claude Code#17364:Issue comment#23968 (comment)createdbypytorch-bot[bot]Bot
  Oct 18, 20262s
  More actions for workflow run 17364