All workflows

Workflow runs

• Improve the dimension checks for the FP8 recipes (#2894)

  failed:
  Deploy nightly docs#12:Commit89a4a3fpushedbyrangsimanketkaew
  main

  Nov 6, 20261m 40s
  More actions for workflow run 12

• Improve the dimension checks for the FP8 recipes (#2894)

  completed successfully:
  Minimum supported versions#1:Commit89a4a3fpushedbyrangsimanketkaew
  main

  Nov 6, 202652m 25s
  More actions for workflow run 1

• [All] Guard THD learnable dSink on older cuDNN (#3470)

  failed:
  Deploy nightly docs#11:Commitc3081a5pushedbyrangsimanketkaew
  main

  Oct 15, 20261m 59s
  More actions for workflow run 11

• [PyTorch] Fix NVFP4 weight views of the single-group fused grouped ML…

  failed:
  Deploy nightly docs#10:Commit2e959f3pushedbyrangsimanketkaew
  main

  Oct 12, 20261m 52s
  More actions for workflow run 10

• Fix MXFP8 ONNX block quantization attributes (#3592)

  failed:
  Deploy nightly docs#9:Commit9d4bd38pushedbyrangsimanketkaew
  main

  Oct 6, 20261m 47s
  More actions for workflow run 9

• [Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI (#3137)

  failed:
  Deploy nightly docs#8:Commiteb56ba2pushedbyrangsimanketkaew
  main

  Sep 29, 20261m 29s
  More actions for workflow run 8

• [PyTorch][CP] Reduce P2P forward peak memory: O(C) _ O(1) (#2916)

  failed:
  Deploy nightly docs#7:Commitf5f4e83pushedbyrangsimanketkaew
  main

  Sep 23, 20262m 23s
  More actions for workflow run 7

• [Common] Add non-TMA MXFP8 cast-only kernels for specialized rowwise-…

  failed:
  Deploy nightly docs#6:Commit9233c73pushedbyrangsimanketkaew
  main

  Sep 19, 20261m 47s
  More actions for workflow run 6

• Cutlass Upgrade to 4.8 (#3443)

  failed:
  Deploy nightly docs#5:Commit9c735bfpushedbyrangsimanketkaew
  main

  Sep 14, 20261m 54s
  More actions for workflow run 5

• [All] Refactor fused attention APIs with cuDNN-frontend support check…

  failed:
  Deploy nightly docs#4:Commitf689f8fpushedbyrangsimanketkaew
  main

  Sep 10, 20262m 4s
  More actions for workflow run 4

• [PyTorch] Fix NaN expert weight gradients at num_groups == 1 with SRe…

  failed:
  Deploy nightly docs#3:Commit39a5401pushedbyrangsimanketkaew
  main

  Sep 9, 20262m 4s
  More actions for workflow run 3

• [Common] Preserve shared-memory pointer provenance in TMA kernels (#3…

  failed:
  Deploy nightly docs#2:Commit5f6105bpushedbyrangsimanketkaew
  main

  Sep 7, 20261m 34s
  More actions for workflow run 2

• [PyTorch] Fix GIL/refcount abort in Comm+GEMM overlap and NCCL-EP ini…

  failed:
  Deploy nightly docs#1:Commit6377ca1pushedbyrangsimanketkaew
  main

  Jul 12, 20261m 33s
  More actions for workflow run 1