- 13 Dec, 2021 1 commit
-
-
Hubert Lu authored
-
- 04 Oct, 2021 1 commit
-
-
Jeff Daily authored
-
- 25 Feb, 2021 1 commit
-
-
Jeff Daily authored
This reverts commit bdd481d1.
-
- 21 Jan, 2021 1 commit
-
-
Jeff Daily authored
use __launch_bounds__(1024) for multi_tensor_apply, re-enable skipped tests
-
- 18 Jan, 2021 1 commit
-
-
Jeff Daily authored
-
- 05 Aug, 2020 1 commit
-
-
ngimel authored
* add device guards to the optimizers * add untracked file * set deviceGuard in multi_tensor_apply * address review comments; fix lamb * indent * typo
-
- 21 May, 2020 1 commit
-
-
Jeff Daily authored
-
- 12 May, 2020 1 commit
-
-
Chaitanya Sri Krishna Lolla authored
-
- 27 Feb, 2020 1 commit
-
-
mcarilli authored
* NHWC support for multi tensor apply * compilation fix for version<=1.4
-
- 06 Sep, 2019 1 commit
-
-
mcarilli authored
* Pushing for build tests * Contrib files * Removing deprecated checks
-
- 03 Jul, 2019 2 commits
-
-
Michael Carilli authored
-
Michael Carilli authored
-
- 31 May, 2019 1 commit
-
-
mcarilli authored
* Existing tests passing, still need to add per-tensor tests * Test is passing, still need to measure performance * ILP for l2norm functor
-
- 12 Mar, 2019 1 commit
-
-
Michael Carilli authored
-
- 10 Mar, 2019 1 commit
-
-
Natalia Gimelshein authored
-
- 28 Feb, 2019 1 commit
-
-
Michael Carilli authored
-
- 24 Feb, 2019 1 commit
-
-
Michael Carilli authored
-
- 22 Feb, 2019 1 commit
-
-
Michael Carilli authored
Allow multi-tensor unscale to handle FP16 output, so it can also be used for copy-scatter. Rename some options.
-
- 19 Feb, 2019 1 commit
-
-
Michael Carilli authored
-