executorch
executorch copied to clipboard
log_softmax
Summary:
Use the following property to implement log_softmax
log(exp(x_i) / sum(exp(x_j))) = x_i - log(sum(exp(x_j)))
- numerically stable, since we can avoid log(small_number) -> -\infty
- reusing existing
softmax
shader to generate variants
Differential Revision: D56688093
:link: Helpful Links
:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3411
- :page_facing_up: Preview Python docs built from this PR
Note: Links to docs will display an error until the docs builds have been completed.
:x: 2 New Failures
As of commit 5de743fa3bbd066d4d55ecd947ad687a6134fc25 with merge base 2c1e2836e321d9205eeb7662ffcfe51aaece6f98 ():
NEW FAILURES - The following jobs have failed:
-
pull / unittest / linux (buck2) / linux-job (gh)
backends/arm/test/ops/test_view.py::TestSimpleView::test_view_tosa_BI_2
-
pull / unittest / macos (buck2) / macos-job (gh)
backends/arm/test/ops/test_view.py::TestSimpleView::test_view_tosa_BI_3
This comment was automatically generated by Dr. CI and updates every 15 minutes.
This pull request was exported from Phabricator. Differential Revision: D56688093
This pull request was exported from Phabricator. Differential Revision: D56688093
This pull request was exported from Phabricator. Differential Revision: D56688093
This pull request was exported from Phabricator. Differential Revision: D56688093
This pull request was exported from Phabricator. Differential Revision: D56688093
This pull request was exported from Phabricator. Differential Revision: D56688093
This pull request has been merged in pytorch/executorch@5b65163c37f77cd98073783745396dae847864d7.