Skip to content

[Optimization] merge matmul and add #6986

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

Open
BingooYang wants to merge 7 commits into
base: develop
Choose a base branch
from
Open

[Optimization] merge matmul and add #6986

Changes from 2 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
c5ae0bc
merge matmul and add
BingooYang Mar 24, 2026
0100aaa
modify format
BingooYang Mar 24, 2026
47cbb7b
using paddle.nn.functional.linear
BingooYang Mar 24, 2026
a89ec24
using _C_ops.linear
BingooYang Mar 26, 2026
c594ab1
using paddle.nn.functional.linear
BingooYang Mar 27, 2026
d7bca72
add FLAGS_use_legacy_linear env var in test case
BingooYang Mar 29, 2026
70c2524
fix format
BingooYang Mar 29, 2026
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
5 changes: 2 additions & 3 deletions fastdeploy/model_executor/layers/linear.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,10 +82,9 @@ def process_loaded_weights(self, layer, weights) -> None:
layer.weight.set_value(weights)

def apply(self, layer: nn.Layer, x: paddle.Tensor) -> paddle.Tensor:
linear_out = paddle.matmul(x, layer.weight)
if layer.with_bias:
linear_out = paddle.add(linear_out, layer.bias)
return linear_out
return paddle._C_ops.linear(x, layer.weight, layer.bias)
return paddle.matmul(x, layer.weight)


class LinearBase(nn.Layer):
Expand Down
Loading