saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix GPU memory leak on TensorRT (#4172)

Browse source
This commit is contained in:
Matthew Hill 2020-06-10 19:56:51 -04:00 committed by GitHub
parent af0750ba1b
commit 117b2e7743
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
View file

@ -1018,6 +1018,8 @@ common::Status TensorrtExecutionProvider::Compile(const std::vector<onnxruntime:
for (int i = 0, end = num_binding_outputs; i < end; ++i) {
if (output_types[i] == ONNX_TENSOR_ELEMENT_DATA_TYPE_INT64) {
cuda::Impl_Cast<int32_t, int64_t>(reinterpret_cast<int32_t*>(buffers[i + num_binding_inputs]), ort.GetTensorMutableData<int64_t>(output_tensor[i]), output_dim_sizes[i]);
cudaDeviceSynchronize();
cudaFree(buffers[i + num_binding_inputs]);
}
}