onnxruntime
[TensorRT EP] Remove cudaDeviceSynchronize and use cudaAllocator for scratch buffers
#5714
Merged

[TensorRT EP] Remove cudaDeviceSynchronize and use cudaAllocator for scratch buffers #5714

jywu-msft merged 3 commits into master from jywu_trt_sync
jywu-msft
jywu-msft use cuda allocator, remove cudaDeviceSync call
7289d1fc
jywu-msft use unique_ptr for scratch buffers
6fea614f
jywu-msft Merge branch 'master' of https://github.com/microsoft/onnxruntime int…
a91c2489
jywu-msft jywu-msft requested a review from HectorSVC HectorSVC 5 years ago
jywu-msft jywu-msft requested a review from stevenlix stevenlix 5 years ago
jywu-msft jywu-msft requested a review 5 years ago
HectorSVC
HectorSVC approved these changes on 2020-11-05
jywu-msft jywu-msft merged c46515cd into master 5 years ago
jywu-msft jywu-msft deleted the jywu_trt_sync branch 5 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone