Skip to content

Actions: tdophung/TransformerEngine

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
29 workflow runs
29 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 convergence table rendering in README.rst (#3109) Deploy nightly docs #25: Commit 4bf946d pushed by tdophung
1m 39s main
main
1m 39s
[Fix] Fix CUTLASS grouped GEMM segfault for empty groups (#3067) Deploy nightly docs #24: Commit b24049b pushed by tdophung
1m 33s main
main
1m 33s
Changed VERSION to 2.17.0.dev0 Deploy nightly docs #23: Commit 583d2d1 pushed by tdophung
1m 30s main
main
1m 30s
Graph Safe support for TE Grouped linear Op (#2923) Deploy nightly docs #22: Commit 3ded616 pushed by tdophung
1m 54s main
main
1m 54s
[Core] Remove unused NVFP4 quantize kernel (#2946) Deploy nightly docs #21: Commit 7e8bc98 pushed by tdophung
1m 46s main
main
1m 46s
Correctly pad scaling factor inverses to satisfy cuteDSL requirements… Deploy nightly docs #20: Commit 01aef4f pushed by tdophung
2m 14s main
main
2m 14s
[Common] Reduced padding kernel compilation time (#2827) Deploy nightly docs #19: Commit 264da2b pushed by tdophung
1m 43s main
main
1m 43s
Comm gemm fixes (#2818) Deploy nightly docs #18: Commit 86edac4 pushed by tdophung
1m 28s main
main
1m 28s
[Core] MXFP8 grouped GEMM + tensor-scaled FP8 fixes (#2748) Deploy nightly docs #17: Commit ef703e5 pushed by tdophung
16m 5s main
main
16m 5s
WAR sort_chunks_by_index intermittent failures in L0 JAX unitttest pa… Deploy nightly docs #16: Commit d40b9de pushed by tdophung
1m 32s main
main
1m 32s
[JAX] Remove GSPMD tests + adding guards and warning msg for GSPMD ru… Deploy nightly docs #15: Commit 39d249b pushed by tdophung
1m 38s main
main
1m 38s
[JAX] TE Permutation integration to Maxtext (#2672) Deploy nightly docs #14: Commit 5d112e3 pushed by tdophung
1m 33s main
main
1m 33s
[Common] Disabled the tuned NVFP4 kernels (#2615) Deploy nightly docs #13: Commit a0a89a8 pushed by tdophung
1m 20s main
main
1m 20s
[JAX] Fix cb.CUDAOptions usage for Triton 3.6.0 (#2610) Deploy nightly docs #12: Commit 8bf37f0 pushed by tdophung
1m 14s main
main
1m 14s
Fixed the year to 2026 (#2611) Deploy nightly docs #11: Commit 36f4e45 pushed by tdophung
1m 25s main
main
1m 25s
[PyTorch] Bunch of fixes for cpu offloading (#2535) Deploy nightly docs #10: Commit fe8fad5 pushed by tdophung
2m 9s main
main
2m 9s
[docs] Getting started refactor (#2534) Deploy nightly docs #9: Commit a976740 pushed by tdophung
1m 31s main
main
1m 31s
Document environment variables (#2552) Deploy nightly docs #8: Commit 27dc83b pushed by tdophung
1m 46s main
main
1m 46s
Fix ptxas compilation on sm103 for triton kernels (#2539) Deploy nightly docs #7: Commit 97a09c2 pushed by tdophung
1m 28s main
main
1m 28s
Jax primitives for permutation on single GPU (#2473) Deploy nightly docs #6: Commit 46c6ef3 pushed by tdophung
1m 30s main
main
1m 30s
[PyTorch] Change order of args in another permutation triton kernel … Deploy nightly docs #5: Commit e05f87e pushed by tdophung
1m 37s main
main
1m 37s
[Pytorch][Bug]MXFP8 Split tensor Bug fix (#2427) Deploy nightly docs #4: Commit c09411d pushed by tdophung
1m 25s main
main
1m 25s
Add primary weighs fp8 support for mxfp8 (#2055) Deploy nightly docs #3: Commit d126cdd pushed by tdophung
1m 30s main
main
1m 30s
Set 0 as the size of dummy tensors to reduce memory usage. Documentation #1: Pull request #1 opened by mingxu1067
1m 55s mingxu1067:mingh/set_dummy_with_zero_sizes
mingxu1067:mingh/set_dummy_with_zero_sizes
1m 55s
Set 0 as the size of dummy tensors to reduce memory usage. Lint #1: Pull request #1 opened by mingxu1067
3m 16s mingxu1067:mingh/set_dummy_with_zero_sizes
mingxu1067:mingh/set_dummy_with_zero_sizes
3m 16s