Skip to content

[BugFix] fix gelu_tanh.cu #6365

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
xiaozude wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

[BugFix] fix gelu_tanh.cu #6365

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0d28c00
[BugFix] fix gelu_tanh.cu
xiaozude Feb 5, 2026
e3a794b
Merge branch 'develop' into pr2
EmmonsCurse Feb 5, 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
2 changes: 1 addition & 1 deletion custom_ops/gpu_ops/gelu_tanh.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ std::vector<paddle::Tensor> GeluTanh(paddle::Tensor& input) {
DISPATCH_FLOAT_FP6_DTYPE(input.dtype(), scalar_t, {
uint32_t vec_size = 16 / sizeof(scalar_t);
dim3 grid(num_tokens);
dim3 block(std::max(d / vec_size, 1024U));
dim3 block(std::min(d / vec_size, 1024U));

#ifdef PADDLE_WITH_CUSTOM_DEVICE_METAX_GPU
gelu_tanh_kernel<scalar_t><<<grid, block, 0, stream>>>(
Expand Down
Loading