transformer_engine/paddle/cpp_extensions.py · 430d5d5a65f7a729468c2aebe4c957b34156fcd0 · OpenDAS / TransformerEngine

[Paddle] Add main_grad (#779) · 430d5d5a

Shijie authored May 18, 2024



* support main_grad
Signed-off-by: Shijie Wang <jaywan@nvidia.com>

* update main_grad and fuse_wgrad_accumulation
Signed-off-by: Shijie Wang <jaywan@nvidia.com>

* fix ci errors
Signed-off-by: Shijie Wang <jaywan@nvidia.com>

* minor change
Signed-off-by: Shijie Wang <jaywan@nvidia.com>

---------
Signed-off-by: Shijie Wang <jaywan@nvidia.com>

430d5d5a

cpp_extensions.py 31.7 KB

Replace cpp_extensions.py