saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-26 22:35:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix a prefast warning (#15343)

Browse source 
### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->


https://aiinfra.visualstudio.com/ONNX%20Runtime/_workitems/edit/14272/?triage=true
This commit is contained in:
Ye Wang 2023-04-03 18:25:25 -07:00 committed by GitHub
parent 44027797b0
commit dec11afb83
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
onnxruntime/contrib_ops/cuda/decoder/decoder_masked_multihead_attention.cc
View file

@ -107,9 +107,13 @@ Status DecoderMaskedMultiHeadAttention<T1, T2>::ComputeInternal(OpKernelContext*
output_shape[2] = static_cast<int64_t>(parameters.v_hidden_size);
Tensor* output = context->Output(0, output_shape);
// Present input will have the same shape as the past input
Tensor* present_key = context->Output(kPresentOutputIndex, past_key->Shape());
Tensor* present_value = context->Output(kPresentOutputIndex + 1, past_value->Shape());
std::vector<int64_t> present_dims{
parameters.batch_size, parameters.num_heads,
past_present_share_buffer_ ? parameters.max_sequence_length : parameters.total_sequence_length,
parameters.head_size};
TensorShape present_shape(present_dims);
Tensor* present_key = context->Output(kPresentOutputIndex, present_shape);
Tensor* present_value = context->Output(kPresentOutputIndex + 1, present_shape);
auto cuda_stream = Stream(context);
@ -139,6 +143,7 @@ Status DecoderMaskedMultiHeadAttention<T1, T2>::ComputeInternal(OpKernelContext*
} else {
// Sanity check
ORT_ENFORCE(past_present_share_buffer_);
ORT_ENFORCE(past_key != nullptr && past_value != nullptr);
auto* present_key_data = present_key->MutableData<T1>();
auto* present_value_data = present_value->MutableData<T1>();