Commits · d6ff6f4db9ee30429b9b3b4b06a2a9d20778c6b1 · OpenDAS / TransformerEngine

04 Jan, 2023 1 commit

Docs: remove build warnings and add FP8 caching note (#44) · d6ff6f4d

Kirthi Shankar Sivamani authored Jan 04, 2023



* docs: remove build warnings and add FP8 caching note
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* add comment about amax history
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

d6ff6f4d

02 Dec, 2022 1 commit

Link performance optimization tutorial to docs (#36) · 0291a608

Przemyslaw Tredak authored Dec 02, 2022


Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>

0291a608

18 Nov, 2022 1 commit

Documentation for advanced performance optimizations (#20) · 8e7f4c8c

Tim Moon authored Nov 18, 2022



* Documentation for advanced perf optimizations

Fix bug where we were doing backward passes inside fp8_autocast in example notebooks.
Signed-off-by: Tim Moon <tmoon@nvidia.com>

* Minor tweaks to advanced perf optimization docs

Review suggestions from @ptrendx
Signed-off-by: Tim Moon <tmoon@nvidia.com>

* Rewording sequence parallelism in advanced perf optimization docs

Review suggestion from @ksivaman
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Signed-off-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: Tim Moon <tmoon@nvidia.com>
Signed-off-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

8e7f4c8c