Skip to content

CI测试不review optimize phi::GPUContext in paddle/phi/kernels/selected_rows/ [phi_ops] #77606

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
co63oc wants to merge 3 commits into
base: develop
Choose a base branch
from
+5 −5
Open

CI测试不review optimize phi::GPUContext in paddle/phi/kernels/selected_rows/ [phi_ops] #77606

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
67cf95d
optimize phi::GPUContext in paddle/phi/kernels/selected_rows/
co63oc Jan 31, 2026
24e45d5
Fix
co63oc Feb 1, 2026
7a47270
Fix
co63oc Feb 4, 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 paddle/phi/kernels/selected_rows/gpu/uniform_random_batch_size_like_kernel.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ void GPUUniformRandomKernel(const Context& dev_ctx,
out->set_height(input.height());
DenseTensor* tensor = out->mutable_value();
dev_ctx.template Alloc<T>(tensor);
funcs::UniformRandom<T>(reinterpret_cast<const phi::GPUContext&>(dev_ctx),
funcs::UniformRandom<T>(reinterpret_cast<const GPUContext&>(dev_ctx),
tensor,
seed,
min,
Expand Down
8 changes: 4 additions & 4 deletions paddle/phi/kernels/sparse/gpu/sparse_attention_kernel.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,7 +206,7 @@ input: sparse C in CSR format (num_rows,num_rows)
output: sparse C after softmax operation
*/
template <typename DeviceContext, typename T>
void SparseSoftmaxForward(const phi::GPUContext& dev_ctx,
void SparseSoftmaxForward(const GPUContext& dev_ctx,
const DenseTensor* offset,
const DenseTensor* columns,
DenseTensor* input,
Expand Down Expand Up @@ -319,7 +319,7 @@ void SparseSoftmaxForward(const phi::GPUContext& dev_ctx,
}

template <typename DeviceContext, typename T>
void SparseSoftmaxBackward(const phi::GPUContext& dev_ctx,
void SparseSoftmaxBackward(const GPUContext& dev_ctx,
const DenseTensor* offset,
const DenseTensor* columns,
DenseTensor* dx,
Expand Down Expand Up @@ -450,7 +450,7 @@ input: dense A (num_rows,num_cols), dense B (num_rows,num_cols)
output: sparse C in CSR format (num_rows,num_rows)
*/
template <typename DeviceContext, typename T>
void DotSdd(const phi::GPUContext& dev_ctx,
void DotSdd(const GPUContext& dev_ctx,
const DenseTensor* a,
const DenseTensor* b,
const DenseTensor* c_offset,
Expand Down Expand Up @@ -550,7 +550,7 @@ input: sparse A in CSR format (num_rows,num_rows), dense B (num_rows,num_cols)
output: dense C (num_rows,num_cols)
*/
template <typename DeviceContext, typename T>
void DotDsd(const phi::GPUContext& dev_ctx,
void DotDsd(const GPUContext& dev_ctx,
const DenseTensor* a_offset,
const DenseTensor* a_columns,
const DenseTensor* a_value,
Expand Down
Loading