- 27 Aug, 2024 1 commit
-
-
Kirthi Shankar Sivamani authored
Signed-off-by:Kirthi Shankar Sivamani <ksivamani@nvidia.com>
-
- 22 Aug, 2024 1 commit
-
-
NVJiangShao authored
* Add permutation functions * Add permutation ops * Remove the dependency on cutlass * Move permutation.py out of module dir * Rewrite the unit test and enable skipping if FP8 is unavailable * Rename exposed C++ API and reorder its parameters + take NVTETensor as inputs * Use Float8Tensor for FP8 input * Move dtype to ctx --------- Signed-off-by:
Jiang Shao <jiangs@nvidia.com> Co-authored-by:
Qi Zhang <qizhang@nvidia.com> Co-authored-by:
Phuong Nguyen <36155692+phu0ngng@users.noreply.github.com>
-
- 21 Aug, 2024 1 commit
-
-
Tim Moon authored
* Perform scale-inv update in cast-transpose kernels Signed-off-by:
Tim Moon <tmoon@nvidia.com> * Perform scale-inv update in cast and activation kernels Signed-off-by:
Tim Moon <4406448+timmoon10@users.noreply.github.com> * Debug mismatched dtypes Signed-off-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
- 14 Aug, 2024 1 commit
-
-
Tim Moon authored
* Bump minimum CUDA version to 12.0 Signed-off-by:
-
- 12 Aug, 2024 1 commit
-
-
Phuong Nguyen authored
* added threading build back * integrating threading for pytorch and paddle extensions * added messages --------- Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com> Co-authored-by:
-
- 25 Jul, 2024 2 commits
-
-
Kirthi Shankar Sivamani authored
* Fixes for wheels Signed-off-by:
-
Kirthi Shankar Sivamani authored
* Specify python version Signed-off-by:
-
- 24 Jul, 2024 1 commit
-
-
Tim Moon authored
* Set minimum CMake version to 3.21 Stop linking to nvtx. Signed-off-by:
-
- 08 Jul, 2024 1 commit
-
-
Phuong Nguyen authored
* add parallel build without pyproject Signed-off-by:
-
- 13 Jun, 2024 1 commit
-
-
Alp Dener authored
* added DL framework callbacks for bootstrapping userbuffers without MPI Signed-off-by:
Alp Dener <adener@nvidia.com> * removed userbuffers availability check in TE modules since userbuffers is now always compiled Signed-off-by:
-
- 12 Jun, 2024 1 commit
-
-
Oleg Goncharov authored
* Merged CT+dbias+dact into a single template Signed-off-by:
Oleg Goncharov <ogoncharov@nvidia.com> * Moved gated activations ifrom the cast_transpose_fused ito a sseparate cpp file Signed-off-by:
Oleg Goncharov <64355998+Oleg-Goncharov@users.noreply.github.com> * Update transformer_engine/common/transpose/cast_transpose_fusion.cu Co-authored-by:
-
- 14 May, 2024 1 commit
-
-
cyanguwa authored
* use 3rdparty cudnn-frontend cmake to find cuDNN Signed-off-by:
Charlene Yang <8636796+cyanguwa@users.noreply.github.com> * add check for 3rdparty/cudnn-frontend module Signed-off-by:
-
- 19 Apr, 2024 1 commit
-
-
Tim Moon authored
* Add NVRTC kernels for cast-transpose Signed-off-by:
-
- 08 Feb, 2024 2 commits
-
-
Tim Moon authored
* Implement fused kernel for FP8 scale update Signed-off-by:
-
Oleg Goncharov authored
* Added new unfused softmax cuda kernel to support causal attention mask Signed-off-by:
-
- 25 Jan, 2024 1 commit
-
-
Xin Yao authored
* fused apply rope Signed-off-by:
Xin Yao <xiny@nvidia.com> * Apply suggestions from code review Co-authored-by:
Xin Yao <yaox12@outlook.com> * resolve comments Signed-off-by:
Przemek Tredak <ptredak@nvidia.com> * add support for bshd format Signed-off-by:
-
- 03 Jan, 2024 1 commit
-
-
Przemyslaw Tredak authored
Signed-off-by:
-
- 23 Oct, 2023 1 commit
-
-
niboshi authored
Signed-off-by:niboshi <niboshi000@gmail.com>
-
- 01 Jul, 2023 1 commit
-
-
Tim Moon authored
Signed-off-by:
-
- 22 Jun, 2023 1 commit
-
-
cyanguwa authored
* add long sequence support and unify three backends for fused attention Signed-off-by:
-
- 13 Jun, 2023 1 commit
-
-
Przemyslaw Tredak authored
* Added ReLU and GLU variants to common Signed-off-by:
Przemyslaw Tredak <ptrendx@gmail.com> Signed-off-by:
-
- 31 May, 2023 1 commit
-
-
Tim Moon authored
* Refactor Setuptools build system Successfully launches CMake install, but installs CMake extensions in temp dir. Signed-off-by:
-
- 19 May, 2023 1 commit
-
-
Tim Moon authored
* Initial implementation of NVRTC infrastructure Signed-off-by:
-
- 09 May, 2023 1 commit
-
-
zlsh80826 authored
* Add fused attention unit tests Signed-off-by:
Reese Wang <rewang@nvidia.com> * Use NVTE_* enums Signed-off-by:
-
- 21 Apr, 2023 2 commits
-
-
cyanguwa authored
* Add FP8 fused attention to TE for PyTorch Signed-off-by:
Charlene Yang <charleney@nvidia.com> * add license for cudnn-frontend, modify installation requirements, and refactor some headers for aesthetics Signed-off-by:
-
Kirthi Shankar Sivamani authored
* Initial refactor; linker error Signed-off-by:
Sangkug Lym <slym@nvidia.com> Signed-off-by:
-
- 19 Apr, 2023 1 commit
-
-
Kirthi Shankar Sivamani authored
* Port initial changes Co-authored-by:
Vasudevan Rengasamy <vrengasamy@nvidia.com> Signed-off-by:
-
- 21 Mar, 2023 1 commit
-
-
vasunvidia authored
* Initial commit for fp8_transpose_dbias kernel Signed-off-by:
-
- 24 Feb, 2023 1 commit
-
-
Jeng Bai-Cheng authored
* add building workflow for jax modules Signed-off-by:
Ryan Jeng <rjeng@nvidia.com> * replace bit_cast with reinterpret_cast Signed-off-by:
Jeng Bai-Cheng <jeng1220@users.noreply.github.com> * Update tests/jax/test_custom_call_shape.py fix typo Co-authored-by:
-
- 12 Jan, 2023 1 commit
-
-
Przemyslaw Tredak authored
* Add NVTX to TE modules Signed-off-by:
-
- 09 Jan, 2023 1 commit
-
-
zlsh80826 authored
* Add rmsnorm kernels Signed-off-by:
-
- 03 Jan, 2023 1 commit
-
-
Przemyslaw Tredak authored
Signed-off-by:
-
- 01 Dec, 2022 1 commit
-
-
Kirthi Shankar Sivamani authored
* Make fused softmax kernels PyTorch independent Co-authored-by:
Sean Lee <selee@nvidia.com> Signed-off-by:
-
- 28 Nov, 2022 1 commit
-
-
Tim Moon authored
* Add kernel for multi-tensor cast-transpose Signed-off-by:
-
- 28 Sep, 2022 1 commit
-
-
Przemek Tredak authored
Co-authored-by:
-
