Skip to content

[webgpu] Throw errors for graph catpure when not implemented #26604

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
wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −0
Open

[webgpu] Throw errors for graph catpure when not implemented #26604

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 3 additions & 0 deletions onnxruntime/contrib_ops/webgpu/bert/attention.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -522,6 +522,9 @@ Status ApplyAttention(const Tensor* Q, const Tensor* K, const Tensor* V, const T
const Tensor* past_key, const Tensor* past_value, Tensor* output, Tensor* present_key, Tensor* present_value,
Tensor* output_qk, WebgpuAttentionParameters& parameters, onnxruntime::webgpu::ComputeContext& context,
const Tensor* head_sink, const Tensor* seqlen_k, int local_window_size) {
if (context.IsGraphCaptureEnabled()) {
ORT_NOT_IMPLEMENTED("Graph capture not implemented for non flash attention path");
}
const int output_count = std::min({context.OutputCount(), 1 + (past_key != nullptr ? 1 : 0) + (past_value != nullptr ? 1 : 0)});
const int past_sequence_length = output_count > 1 ? parameters.past_sequence_length_ : 0;
const int total_sequence_length =
Expand Down
Loading