Skip to content

Actions: NVIDIA/TransformerEngine

Actions

Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docs.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
Use cuDNN for row-scaled NVFP4 grouped GEMM Documentation #19196: Pull request #3042 synchronize by ziang-and
Action required zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
Action required
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19195: Pull request #3244 synchronize by YangFei1990
1m 48s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
1m 48s
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19194: Pull request #3244 synchronize by YangFei1990
39s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
39s
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19193: Pull request #3244 synchronize by YangFei1990
2s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
2s
Use cuDNN for row-scaled NVFP4 grouped GEMM Documentation #19192: Pull request #3042 synchronize by ziang-and
Action required zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
Action required
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19191: Pull request #3244 synchronize by pre-commit-ci Bot
2m 29s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
2m 29s
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19190: Pull request #3244 synchronize by YangFei1990
1m 57s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
1m 57s
Use cuDNN for row-scaled NVFP4 grouped GEMM Documentation #19189: Pull request #3042 synchronize by ziang-and
Action required zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
zianglih:codex/cudnn-row-scale-nvfp4-grouped-gemm
Action required
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19188: Pull request #3244 synchronize by pre-commit-ci Bot
4h 57m 55s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
4h 57m 55s
[Pytorch] Add support for row-wise quanted input for grouped gemm Documentation #19187: Pull request #3244 synchronize by YangFei1990
1m 23s YangFei1990:mxfp8_input_groupedgemm
YangFei1990:mxfp8_input_groupedgemm
1m 23s
Add support for fused Q Up-Proj GEMM/RoPE/Quant. Documentation #19186: Pull request #3303 synchronize by sudhakarsingh27
5h 19m 12s chaseblock:qrope_fusion
chaseblock:qrope_fusion
5h 19m 12s
Add support for fused Q Up-Proj GEMM/RoPE/Quant. Documentation #19185: Pull request #3303 synchronize by chaseblock
18m 26s chaseblock:qrope_fusion
chaseblock:qrope_fusion
18m 26s
[JAX] Migrate EP collective-stream annotation to region-based compute_on Documentation #19184: Pull request #3304 synchronize by phu0ngng
18m 38s phu0ngng:jax_compute_on_version
phu0ngng:jax_compute_on_version
18m 38s
[Pytorch] Enable TE Sequential Op to consume extra_outputs from a previously run Op Documentation #19183: Pull request #3320 synchronize by vthumbe1503
1m 27s vthumbe1503:enable_extra_out_consumption
vthumbe1503:enable_extra_out_consumption
1m 27s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI Documentation #19182: Pull request #3137 synchronize by pre-commit-ci Bot
2m 2s kainzhong:cutedsl_mxfp8_common
kainzhong:cutedsl_mxfp8_common
2m 2s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI Documentation #19181: Pull request #3137 synchronize by kainzhong
1m 26s kainzhong:cutedsl_mxfp8_common
kainzhong:cutedsl_mxfp8_common
1m 26s
[JAX] Migrate EP collective-stream annotation to region-based compute_on Documentation #19180: Pull request #3304 synchronize by phu0ngng
1m 25s phu0ngng:jax_compute_on_version
phu0ngng:jax_compute_on_version
1m 25s
Improve device-init grouped linear module with single grouped weight support Documentation #19179: Pull request #3224 synchronize by zhongbozhu
19m 9s zhongbozhu:improve_device_grouped_linear
zhongbozhu:improve_device_grouped_linear
19m 9s
[Common][PyTorch] EP dispatch with unfused MXFP8 quantization Documentation #19178: Pull request #3270 synchronize by phu0ngng
18m 18s phu0ngng:ep_mxfp8
phu0ngng:ep_mxfp8
18m 18s
[Pytorch] Enable TE Sequential Op to consume extra_outputs from a previously run Op Documentation #19177: Pull request #3320 synchronize by vthumbe1503
1m 35s vthumbe1503:enable_extra_out_consumption
vthumbe1503:enable_extra_out_consumption
1m 35s
[Pytorch] Enable TE Sequential Op to consume extra_outputs from a previously run Op Documentation #19176: Pull request #3320 synchronize by pre-commit-ci Bot
1m 38s vthumbe1503:enable_extra_out_consumption
vthumbe1503:enable_extra_out_consumption
1m 38s
[Pytorch] Enable TE Sequential Op to consume extra_outputs from a previously run Op Documentation #19175: Pull request #3320 synchronize by vthumbe1503
1m 22s vthumbe1503:enable_extra_out_consumption
vthumbe1503:enable_extra_out_consumption
1m 22s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI Documentation #19174: Pull request #3137 synchronize by kainzhong
1m 44s kainzhong:cutedsl_mxfp8_common
kainzhong:cutedsl_mxfp8_common
1m 44s
Improve device-init grouped linear module with single grouped weight support Documentation #19173: Pull request #3224 synchronize by zhongbozhu
19m 8s zhongbozhu:improve_device_grouped_linear
zhongbozhu:improve_device_grouped_linear
19m 8s
[Pytorch] Add function to check if EP is bootstrapped Documentation #19172: Pull request #3321 opened by YangFei1990
1m 23s YangFei1990:expose_bootstrap_ep
YangFei1990:expose_bootstrap_ep
1m 23s