onnxruntime

28f2e57d - Use CUDA callback to release deferred-release buffers (#12883)

Use CUDA callback to release deferred-release buffers (#12883) * Use CUDA callback to release deferred-release buffers Polishment * Minor improvements. 1. Reorder a if-else so that frequent cases are checked first. 2. More documents. * Fix tests. Previously, in CUDAExecutionProvider::OnRunStart, we call GetPerThreadContext in auto& current_deferred_release_event = GetPerThreadContext().GetCurrentDeferredReleaseEvent(); so that a CUDAExecutionProvider always owns an active PerThreadContext and the ReleasePerThreadContext in CUDAExecutionProvider::OnRunEnd is always valid. However, this isn't true after we drop event- based deferred-release code, so we need to check if CUDAExecutionProvider really owns PerThreadContext than call ReleasePerThreadContext if yes. * Follow up for AMD GPU and improve CUDA part's return value.