Skip to content

docs: document softmax's precise argument #4178

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
zcbenz merged 1 commit into from
Aug 11, 2026
Merged

docs: document softmax's precise argument #4178

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion python/src/ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3278,7 +3278,7 @@ void init_ops(nb::module_& m) {
"precise"_a = false,
"stream"_a = nb::none(),
nb::sig(
"def softmax(a: array, /, axis: None | int | Sequence[int] = None, *, stream: StreamOrDevice = None) -> array"),
"def softmax(a: array, /, axis: None | int | Sequence[int] = None, *, precise: bool = False, stream: StreamOrDevice = None) -> array"),
R"pbdoc(
Perform the softmax along the given axis.

Expand All @@ -3293,6 +3293,10 @@ void init_ops(nb::module_& m) {
axis (int or list(int), optional): Optional axis or axes to compute
the softmax over. If unspecified this performs the softmax over
the full array.
precise (bool, optional): Accumulate in ``float32`` for inputs of
lower precision. Otherwise the accumulation type matches the
input, which can lose precision over long reduction axes.
Default: ``False``.

Returns:
array: The output of the softmax.
Expand Down