Skip to content

Actions: rangsimanketkaew/TransformerEngine

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
9 workflow runs
9 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Fix MXFP8 ONNX block quantization attributes (#3592) Deploy nightly docs #9: Commit 9d4bd38 pushed by rangsimanketkaew
1m 47s main
main
1m 47s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI (#3137) Deploy nightly docs #8: Commit eb56ba2 pushed by rangsimanketkaew
1m 29s main
main
1m 29s
[PyTorch][CP] Reduce P2P forward peak memory: O(C) _ O(1) (#2916) Deploy nightly docs #7: Commit f5f4e83 pushed by rangsimanketkaew
2m 23s main
main
2m 23s
[Common] Add non-TMA MXFP8 cast-only kernels for specialized rowwise-… Deploy nightly docs #6: Commit 9233c73 pushed by rangsimanketkaew
1m 47s main
main
1m 47s
Cutlass Upgrade to 4.8 (#3443) Deploy nightly docs #5: Commit 9c735bf pushed by rangsimanketkaew
1m 54s main
main
1m 54s
[All] Refactor fused attention APIs with cuDNN-frontend support check… Deploy nightly docs #4: Commit f689f8f pushed by rangsimanketkaew
2m 4s main
main
2m 4s
[PyTorch] Fix NaN expert weight gradients at num_groups == 1 with SRe… Deploy nightly docs #3: Commit 39a5401 pushed by rangsimanketkaew
2m 4s main
main
2m 4s
[Common] Preserve shared-memory pointer provenance in TMA kernels (#3… Deploy nightly docs #2: Commit 5f6105b pushed by rangsimanketkaew
1m 34s main
main
1m 34s
[PyTorch] Fix GIL/refcount abort in Comm+GEMM overlap and NCCL-EP ini… Deploy nightly docs #1: Commit 6377ca1 pushed by rangsimanketkaew
1m 33s main
main
1m 33s