Skip to content
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

#17013: Update add_bw doc #17363

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+8 −3
Open

#17013: Update add_bw doc #17363

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
11 changes: 8 additions & 3 deletions ttnn/cpp/ttnn/operations/eltwise/binary_backward/binary_backward_pybind.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,7 +713,8 @@ void bind_binary_bw(
py::module& module,
const binary_backward_operation_t& operation,
const std::string_view description,
const std::string_view supported_dtype = "BFLOAT16") {
const std::string_view supported_dtype = "BFLOAT16",
const std::string_view note = "") {
auto doc = fmt::format(
R"doc(

Expand Down Expand Up @@ -747,6 +748,8 @@ void bind_binary_bw(

bfloat8_b/bfloat4_b is only supported on TILE_LAYOUT

{4}

Example:
>>> grad_tensor = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device)
>>> tensor1 = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16, requires_grad=True), layout=ttnn.TILE_LAYOUT, device=device)
Expand All @@ -762,7 +765,8 @@ void bind_binary_bw(
operation.base_name(),
operation.python_fully_qualified_name(),
description,
supported_dtype);
supported_dtype,
note);

bind_registered_operation(
module,
Expand Down Expand Up @@ -1183,7 +1187,8 @@ void py_module(py::module& module) {
module,
ttnn::add_bw,
R"doc(Performs backward operations for add of :attr:`input_tensor_a` and :attr:`input_tensor_b` or :attr:`scalar` with given :attr:`grad_tensor`.)doc",
R"doc(BFLOAT16, BFLOAT8_B)doc");
R"doc(BFLOAT16, BFLOAT8_B)doc",
R"doc(Sharding is not supported.)doc");

detail::bind_binary_bw(
module,
Expand Down
Loading