larroy commented on a change in pull request #16654: Multithreaded Inference
Support
URL: https://github.com/apache/incubator-mxnet/pull/16654#discussion_r354542395
##########
File path: ci/docker/runtime_functions.sh
##########
@@ -1353,6 +1373,19 @@ integrationtest_ubuntu_gpu_cpp_package() {
cpp-package/tests/ci_test.sh
}
+integrationtest_ubuntu_gpu_capi_cpp_package() {
+ set -ex
+ export PYTHONPATH=./python/
+ export LD_LIBRARY_PATH=/work/mxnet/lib:$LD_LIBRARY_PATH
+ python3 -c "import mxnet as mx;
mx.test_utils.download_model(\"imagenet1k-resnet-18\");
mx.test_utils.download_model(\"imagenet1k-resnet-152\");
mx.test_utils.download_model(\"imagenet1k-resnet-50\");"
+ build/tests/cpp/mxnet_unit_tests --gtest_filter="ThreadSafety.*"
+ build/tests/cpp/mxnet_unit_tests --gtest_filter="ThreadSafety.*"
--thread-safety-with-cpu
+ export MXNET_ENGINE_TYPE=NaiveEngine
Review comment:
Why NaiveEngine here? Could you add comments?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
