Skip to content

Enable fp16 channelwise convolution #4808

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
klin2024 wants to merge 4 commits into
base: develop
Choose a base branch
from
+12 −1
Open

Enable fp16 channelwise convolution #4808

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0dea7fd
Enable fp16 channelwise convolution
weizhu12-amd Apr 15, 2026
a708cd9
Merge branch 'develop' into enable_fp16_channelwise
causten Apr 21, 2026
dd5f6ca
Merge branch 'develop' into enable_fp16_channelwise
klin2024 Apr 24, 2026
85b943f
Enable fp16 channelwise convolution
weizhu12-amd Apr 15, 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
3 changes: 2 additions & 1 deletion src/targets/gpu/prefuse_ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,7 +301,8 @@ struct find_channelwise_convolution
auto weights = ins->inputs().back();
auto num_spatial = ins->get_shape().ndim() - 2;

if(input->get_shape().type() != shape::float_type)
if(input->get_shape().type() != shape::float_type and
input->get_shape().type() != shape::half_type)
Copy link

Copilot AI Apr 21, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This condition calls input->get_shape().type() twice and hard-codes two comparisons. For readability and to avoid repeating work, consider caching the type in a local (e.g., auto t = …) and checking membership (e.g., via contains({shape::float_type, shape::half_type}, t)) as done in other GPU type gates (e.g., src/targets/gpu/lowering.cpp:349).

Copilot uses AI. Check for mistakes.
return;

auto v = ins->get_operator().to_value();
Expand Down
Loading