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
[Common][PyTorch] EP dispatch with unfused MXFP8 quantization Documentation #19266: Pull request #3270 synchronize by phu0ngng
1m 47s phu0ngng:ep_mxfp8
phu0ngng:ep_mxfp8
1m 47s
Use a plain parameter for high-precision grouped linear weights Documentation #19265: Pull request #3340 opened by wujingyue
1m 32s wujingyue:grouped-linear-plain-hp-param
wujingyue:grouped-linear-plain-hp-param
1m 32s
Optionally pad QK/V for better kernel selection Documentation #19264: Pull request #3339 synchronize by pre-commit-ci Bot
1m 46s janEbert:optional-mla-pad
janEbert:optional-mla-pad
1m 46s
[PyTorch] [torch.compile] torch.compile support for Linear Documentation #19263: Pull request #3053 synchronize by pggPL
1m 28s pggPL:linear_torch_compile_final_attempt
pggPL:linear_torch_compile_final_attempt
1m 28s
Optionally pad QK/V for better kernel selection Documentation #19262: Pull request #3339 synchronize by janEbert
1m 23s janEbert:optional-mla-pad
janEbert:optional-mla-pad
1m 23s
Plumb FP8+THD Documentation #19261: Pull request #2994 synchronize by sudhakarsingh27
1m 51s sudhakarsingh27:fp8_thd_attention_try2
sudhakarsingh27:fp8_thd_attention_try2
1m 51s
Plumb FP8+THD Documentation #19260: Pull request #2994 synchronize by pre-commit-ci Bot
57s sudhakarsingh27:fp8_thd_attention_try2
sudhakarsingh27:fp8_thd_attention_try2
57s
Plumb FP8+THD Documentation #19259: Pull request #2994 synchronize by sudhakarsingh27
1m 24s sudhakarsingh27:fp8_thd_attention_try2
sudhakarsingh27:fp8_thd_attention_try2
1m 24s
Optionally pad QK/V for better kernel selection Documentation #19258: Pull request #3339 synchronize by pre-commit-ci Bot
1m 34s janEbert:optional-mla-pad
janEbert:optional-mla-pad
1m 34s
Optionally pad QK/V for better kernel selection Documentation #19257: Pull request #3339 opened by janEbert
1m 22s janEbert:optional-mla-pad
janEbert:optional-mla-pad
1m 22s
[Pytorch] Enable TE Op to consume extra_outputs from a previously run Op in TE Sequential Documentation #19256: Pull request #3320 synchronize by vthumbe1503
1m 28s vthumbe1503:enable_extra_out_consumption
vthumbe1503:enable_extra_out_consumption
1m 28s
mxfp8: add swizzled-scale fast path for cast-only quantization Documentation #19255: Pull request #3338 synchronize by pre-commit-ci Bot
1m 58s WanZzzzzz:mxfp8-cast-swizzle-main
WanZzzzzz:mxfp8-cast-swizzle-main
1m 58s
mxfp8: add swizzled-scale fast path for cast-only quantization Documentation #19254: Pull request #3338 opened by WanZzzzzz
1m 21s WanZzzzzz:mxfp8-cast-swizzle-main
WanZzzzzz:mxfp8-cast-swizzle-main
1m 21s
[Bug] use_single_group_runtime_offsets arg is not supported for ScaledSrelu Documentation #19253: Pull request #3328 synchronize by ksivaman
1m 49s vthumbe1503:update_arg_condition
vthumbe1503:update_arg_condition
1m 49s
[common] Improved performance of Group MXFP8 kernels Documentation #19252: Pull request #3337 synchronize by pre-commit-ci Bot
1m 41s Oleg-Goncharov:pr_mxfp8_group_kernels_optimization
Oleg-Goncharov:pr_mxfp8_group_kernels_optimization
1m 41s
[common] Improved performance of Group MXFP8 kernels Documentation #19251: Pull request #3337 opened by Oleg-Goncharov
1m 31s Oleg-Goncharov:pr_mxfp8_group_kernels_optimization
Oleg-Goncharov:pr_mxfp8_group_kernels_optimization
1m 31s
[JAX][Fix] Gate collective-stream compute_on on import and silence pylint Documentation #19250: Pull request #3329 synchronize by phu0ngng
1m 42s phu0ngng:jax_compute_on_version
phu0ngng:jax_compute_on_version
1m 42s
Add a backwards linear function to be used with the fused mla q up-proj Documentation #19249: Pull request #3330 synchronize by chaseblock
2m 0s chaseblock:lin_bwd
chaseblock:lin_bwd
2m 0s
[PyTorch] [torch.compile] torch.compile support for Linear Documentation #19248: Pull request #3053 synchronize by pggPL
1m 30s pggPL:linear_torch_compile_final_attempt
pggPL:linear_torch_compile_final_attempt
1m 30s
[PyTorch] Fine-grained recipe docs Documentation #19247: Pull request #3336 synchronize by negvet
1m 45s negvet:fine_grained_recipe_docs
negvet:fine_grained_recipe_docs
1m 45s
Refactor GroupedLinear quantization dispatch Documentation #19246: Pull request #3326 synchronize by pre-commit-ci Bot
1m 52s negvet:refactor-grouped-quantization
negvet:refactor-grouped-quantization
1m 52s
Refactor GroupedLinear quantization dispatch Documentation #19245: Pull request #3326 synchronize by negvet
1m 25s negvet:refactor-grouped-quantization
negvet:refactor-grouped-quantization
1m 25s
[PyTorch] Fine-grained recipe docs Documentation #19244: Pull request #3336 opened by negvet
1m 54s negvet:fine_grained_recipe_docs
negvet:fine_grained_recipe_docs
1m 54s
Add 2d quant for mxfp8 Documentation #19243: Pull request #2634 synchronize by pre-commit-ci Bot
1m 45s kunlunl:2d_mxfp8
kunlunl:2d_mxfp8
1m 45s
Add 2d quant for mxfp8 Documentation #19242: Pull request #2634 synchronize by kunlunl
1m 23s kunlunl:2d_mxfp8
kunlunl:2d_mxfp8
1m 23s