Skip to content

Skeleton for Attention(23) on CUDA #25684

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

Closed
xadupre wants to merge 3 commits into from
Closed

Skeleton for Attention(23) on CUDA #25684

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
d16b799
Skeleton for Attention(23) on CUDA
xadupre Aug 7, 2025
096d680
Merge branch 'main' of https://github.com/microsoft/onnxruntime into …
xadupre Oct 9, 2025
85a3bed
pass some checks
xadupre Oct 9, 2025
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
9 changes: 5 additions & 4 deletions onnxruntime/core/providers/cpu/llm/attention.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
// Licensed under the MIT License.

#include "core/providers/cpu/llm/attention.h"
#include "core/providers/cpu/llm/attention_helper.h"

#include "core/common/common.h"
#include "core/common/safeint.h"
Expand Down Expand Up @@ -140,10 +141,10 @@ Status Attention<T>::Compute(OpKernelContext* context) const {
const Tensor* past_value = context->Input<Tensor>(5);

AttentionParameters parameters;
std::vector<int64_t> y_shape;
std::vector<int64_t> present_key_shape;
std::vector<int64_t> present_value_shape;
std::vector<int64_t> output_qk_shape;
TensorShape y_shape;
TensorShape present_key_shape;
TensorShape present_value_shape;
TensorShape output_qk_shape;

ORT_ENFORCE(attention_helper::ComputeOutputShapeForAttention(
Q,
Expand Down
2 changes: 1 addition & 1 deletion onnxruntime/core/providers/cpu/llm/attention.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
#include "core/common/common.h"
#include "core/framework/op_kernel.h"
#include "core/platform/threadpool.h"
#include "core/providers/cpu/llm/attention_helper.h"
#include "core/providers/cpu/llm/attention_parameters.h"

namespace onnxruntime {

Expand Down
156 changes: 0 additions & 156 deletions onnxruntime/core/providers/cpu/llm/attention_helper.cc
View file
Open in desktop

This file was deleted.

Loading
Loading