Skip to content

Actions: NVIDIA/TransformerEngine

Actions

Lint

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
lint.yml
2,500+ workflow runs
2,500+ workflow runs

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: TransformerEngineBaseModule quantizers init values type Lint #17071: Pull request #2927 opened by muutot
Action required muutot:dev
muutot:dev
Action required
[PyTorch] Fix stale columnwise data usage Lint #17069: Pull request #2925 opened by ksivaman
2m 19s ksivaman:fix_columnwise_usage_after_eval
ksivaman:fix_columnwise_usage_after_eval
2m 19s
[Common, PyTorch] Add triton mHC kernels & pytorch APIs Lint #17068: Pull request #2790 synchronize by pre-commit-ci Bot
Action required kainzhong:feat/mhc_kernels
kainzhong:feat/mhc_kernels
Action required
[Common, PyTorch] Add triton mHC kernels & pytorch APIs Lint #17067: Pull request #2790 synchronize by kainzhong
2m 59s kainzhong:feat/mhc_kernels
kainzhong:feat/mhc_kernels
2m 59s
Make TE Sequential Grouped linear Op CUDA graphable Lint #17066: Pull request #2923 synchronize by pre-commit-ci Bot
Action required vthumbe1503:grouped_linear_integration_v2
vthumbe1503:grouped_linear_integration_v2
Action required
Make TE Sequential Grouped linear Op CUDA graphable Lint #17065: Pull request #2923 synchronize by vthumbe1503
2m 4s vthumbe1503:grouped_linear_integration_v2
vthumbe1503:grouped_linear_integration_v2
2m 4s
Make TE Sequential Grouped linear Op CUDA graphable Lint #17064: Pull request #2923 synchronize by vthumbe1503
2m 22s vthumbe1503:grouped_linear_integration_v2
vthumbe1503:grouped_linear_integration_v2
2m 22s
[PyTorch] Add pad_between_seqs support for non-CP and CP (A2A and P2P) with FA3 + THD (varlen) Lint #17063: Pull request #2596 synchronize by sudhakarsingh27
2m 20s sudhakarsingh27:flash_attn_pad_bw_seqs
sudhakarsingh27:flash_attn_pad_bw_seqs
2m 20s
[PyTorch] Add pad_between_seqs support for non-CP and CP (A2A and P2P) with FA3 + THD (varlen) Lint #17062: Pull request #2596 synchronize by sudhakarsingh27
1m 39s sudhakarsingh27:flash_attn_pad_bw_seqs
sudhakarsingh27:flash_attn_pad_bw_seqs
1m 39s
Optimizations for MXFP8/NVFP4 dequantize kernels Lint #17061: Pull request #2865 synchronize by YigongQin
Action required YigongQin:yigongq/bwd-dequantize-optim
YigongQin:yigongq/bwd-dequantize-optim
Action required
[PyTorch] Add pad_between_seqs support for non-CP and CP (A2A and P2P) with FA3 + THD (varlen) Lint #17060: Pull request #2596 synchronize by sudhakarsingh27
2m 5s sudhakarsingh27:flash_attn_pad_bw_seqs
sudhakarsingh27:flash_attn_pad_bw_seqs
2m 5s
[Common, PyTorch] Add triton mHC kernels & pytorch APIs Lint #17059: Pull request #2790 synchronize by kainzhong
2m 11s kainzhong:feat/mhc_kernels
kainzhong:feat/mhc_kernels
2m 11s
[Common, PyTorch] Add triton mHC kernels & pytorch APIs Lint #17058: Pull request #2790 synchronize by pre-commit-ci Bot
Action required kainzhong:feat/mhc_kernels
kainzhong:feat/mhc_kernels
Action required
[Common, PyTorch] Add triton mHC kernels & pytorch APIs Lint #17057: Pull request #2790 synchronize by kainzhong
1m 57s kainzhong:feat/mhc_kernels
kainzhong:feat/mhc_kernels
1m 57s
[JAX] Calculate seqlens and offsets in O(N) space instead of O(N*N) space for THD sequences Lint #17056: Pull request #2522 synchronize by KshitijLakhani
2m 4s KshitijLakhani:klakhani/mem-optimize-seqlens-offsets-thd
KshitijLakhani:klakhani/mem-optimize-seqlens-offsets-thd
2m 4s
Correctly pad scaling factor inverses to satisfy cuteDSL requirements Lint #17055: Pull request #2924 opened by ksivaman
2m 8s ksivaman:pad_weight_scale_inv
ksivaman:pad_weight_scale_inv
2m 8s
Remove uncessary ctype being passed to GroupedGEMMQuant kernel Lint #17054: Pull request #2922 synchronize by vthumbe1503
2m 5s vthumbe1503:remove_c_type
vthumbe1503:remove_c_type
2m 5s
Make TE Sequential Grouped linear Op CUDA graphable Lint #17053: Pull request #2923 synchronize by pre-commit-ci Bot
Action required vthumbe1503:grouped_linear_integration_v2
vthumbe1503:grouped_linear_integration_v2
Action required
Make TE Sequential Grouped linear Op CUDA graphable Lint #17052: Pull request #2923 opened by vthumbe1503
1m 55s vthumbe1503:grouped_linear_integration_v2
vthumbe1503:grouped_linear_integration_v2
1m 55s
[PyTorch] Add pad_between_seqs support for non-CP and CP (A2A and P2P) with FA3 + THD (varlen) Lint #17051: Pull request #2596 synchronize by sudhakarsingh27
1m 57s sudhakarsingh27:flash_attn_pad_bw_seqs
sudhakarsingh27:flash_attn_pad_bw_seqs
1m 57s
[PyTorch] Add pad_between_seqs support for non-CP and CP (A2A and P2P) with FA3 + THD (varlen) Lint #17050: Pull request #2596 synchronize by pre-commit-ci Bot
2m 4s sudhakarsingh27:flash_attn_pad_bw_seqs
sudhakarsingh27:flash_attn_pad_bw_seqs
2m 4s
[PyTorch] Add pad_between_seqs support for non-CP and CP (A2A and P2P) with FA3 + THD (varlen) Lint #17049: Pull request #2596 synchronize by sudhakarsingh27
2m 1s sudhakarsingh27:flash_attn_pad_bw_seqs
sudhakarsingh27:flash_attn_pad_bw_seqs
2m 1s
Remove uncessary ctype being passed to GroupedGEMMQuant kernel Lint #17048: Pull request #2922 opened by vthumbe1503
2m 4s vthumbe1503:remove_c_type
vthumbe1503:remove_c_type
2m 4s
[Pyt][Common] Enabling/Guarding sm120 support (non - attention) Lint #17047: Pull request #2833 synchronize by pre-commit-ci Bot
Action required KshitijLakhani:klakhani/maint/sm120-pyt-cpp-support
KshitijLakhani:klakhani/maint/sm120-pyt-cpp-support
Action required
[Pyt][Common] Enabling/Guarding sm120 support (non - attention) Lint #17046: Pull request #2833 synchronize by KshitijLakhani
2m 2s KshitijLakhani:klakhani/maint/sm120-pyt-cpp-support
KshitijLakhani:klakhani/maint/sm120-pyt-cpp-support
2m 2s