tests/pytorch/test_numerics.py · f5d720a058c25f3453c974bd758a47b9e03668a4 · OpenDAS / TransformerEngine

[PyTorch] RNG state support for model parallelism (#473) · 8e757a45

Kirthi Shankar Sivamani authored Oct 12, 2023



* Add class for RNG state tracker.
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Fix docs for checkpoint
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* docs
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

8e757a45

test_numerics.py 33.6 KB

Replace test_numerics.py