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
[JAX] Return max_logit from TE fused attn Documentation #19659: Pull request #3112 synchronize by KshitijLakhani
1m 30s KshitijLakhani:klakhani/feat/return-softmax-stats
KshitijLakhani:klakhani/feat/return-softmax-stats
1m 30s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19658: Pull request #3325 synchronize by pre-commit-ci Bot
2m 11s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
2m 11s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19657: Pull request #3325 synchronize by timmoon10
1m 24s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
1m 24s
[JAX] Return max_logit from TE fused attn Documentation #19656: Pull request #3112 synchronize by pre-commit-ci Bot
1m 27s KshitijLakhani:klakhani/feat/return-softmax-stats
KshitijLakhani:klakhani/feat/return-softmax-stats
1m 27s
Plumb FP8+THD Documentation #19655: Pull request #2994 synchronize by sudhakarsingh27
1m 34s sudhakarsingh27:fp8_thd_attention_try2
sudhakarsingh27:fp8_thd_attention_try2
1m 34s
[JAX] Return max_logit from TE fused attn Documentation #19654: Pull request #3112 synchronize by KshitijLakhani
1m 28s KshitijLakhani:klakhani/feat/return-softmax-stats
KshitijLakhani:klakhani/feat/return-softmax-stats
1m 28s
[JAX] Return max_logit from TE fused attn Documentation #19653: Pull request #3112 synchronize by pre-commit-ci Bot
5m 29s KshitijLakhani:klakhani/feat/return-softmax-stats
KshitijLakhani:klakhani/feat/return-softmax-stats
5m 29s
[JAX] Return max_logit from TE fused attn Documentation #19652: Pull request #3112 synchronize by KshitijLakhani
1m 31s KshitijLakhani:klakhani/feat/return-softmax-stats
KshitijLakhani:klakhani/feat/return-softmax-stats
1m 31s
Use cuDNN's deterministic dprob in the fused grouped MLP Documentation #19651: Pull request #3407 synchronize by ZhiyuLi-Nvidia
1m 35s ZhiyuLi-Nvidia:zhiyul/cudnn-deterministic-dprob
ZhiyuLi-Nvidia:zhiyul/cudnn-deterministic-dprob
1m 35s
Use cuDNN's deterministic dprob in the fused grouped MLP Documentation #19650: Pull request #3407 synchronize by vthumbe1503
1m 31s ZhiyuLi-Nvidia:zhiyul/cudnn-deterministic-dprob
ZhiyuLi-Nvidia:zhiyul/cudnn-deterministic-dprob
1m 31s
Use cuDNN's deterministic dprob in the fused grouped MLP Documentation #19649: Pull request #3407 synchronize by vthumbe1503
1m 26s ZhiyuLi-Nvidia:zhiyul/cudnn-deterministic-dprob
ZhiyuLi-Nvidia:zhiyul/cudnn-deterministic-dprob
1m 26s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19648: Pull request #3325 synchronize by pre-commit-ci Bot
2m 15s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
2m 15s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19647: Pull request #3325 synchronize by timmoon10
1m 25s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
1m 25s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19646: Pull request #3325 synchronize by pre-commit-ci Bot
2m 1s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
2m 1s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19645: Pull request #3325 synchronize by timmoon10
1m 29s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
1m 29s
[PyTorch] Optimize GroupedLinear validation Documentation #19644: Pull request #3405 synchronize by vthumbe1503
1m 27s negvet:optimize_grouped_linear_validation_cpu
negvet:optimize_grouped_linear_validation_cpu
1m 27s
[Common/PyTorch] Grouped weighted-SwiGLU MXFP8 kernel Documentation #19643: Pull request #3315 synchronize by vthumbe1503
1m 49s cael-ling:feature/mxfp8-group-swiglu-recompute
cael-ling:feature/mxfp8-group-swiglu-recompute
1m 49s
[Common/PyTorch] Grouped weighted-SwiGLU MXFP8 kernel Documentation #19642: Pull request #3315 synchronize by pre-commit-ci Bot
Action required cael-ling:feature/mxfp8-group-swiglu-recompute
cael-ling:feature/mxfp8-group-swiglu-recompute
Action required
[Common/PyTorch] Grouped weighted-SwiGLU MXFP8 kernel Documentation #19641: Pull request #3315 synchronize by vthumbe1503
Action required cael-ling:feature/mxfp8-group-swiglu-recompute
cael-ling:feature/mxfp8-group-swiglu-recompute
Action required
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19640: Pull request #3325 synchronize by tdophung
1m 31s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
1m 31s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI Documentation #19639: Pull request #3137 synchronize by kainzhong
1m 22s kainzhong:cutedsl_mxfp8_common
kainzhong:cutedsl_mxfp8_common
1m 22s
[PyTorch] Reduce CPU overhead on eager EP dispatch and combine Documentation #19638: Pull request #3380 synchronize by phu0ngng
1m 25s phu0ngng:ep-pyt
phu0ngng:ep-pyt
1m 25s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI Documentation #19637: Pull request #3137 synchronize by kainzhong
1m 20s kainzhong:cutedsl_mxfp8_common
kainzhong:cutedsl_mxfp8_common
1m 20s
[Common] Experimental CuTeDSL MXFP8 backends in C++ via TVM-FFI Documentation #19636: Pull request #3137 synchronize by kainzhong
1m 32s kainzhong:cutedsl_mxfp8_common
kainzhong:cutedsl_mxfp8_common
1m 32s
Prototype NVFP4 with FP8 UE5M3 block scales Documentation #19635: Pull request #3325 synchronize by tdophung
2m 24s timmoon10:nvfp4-ue5m3-prototype
timmoon10:nvfp4-ue5m3-prototype
2m 24s