Olivia Jain b2247ece25 Make Perf Test Configurable (#7836) ... - Allow anyone to kick off a perf test here. Customize: branch, eps, model selection, cuda version. - Only run shape inference when required. - Kill errored out memory processes. - Remove warmup run. - Clean up script. - Standalone_TRT is it's own "EP" vs as an additional run with TRT EP		2021-06-18 11:11:19 -07:00
..
github	Make Perf Test Configurable (#7836)	2021-06-18 11:11:19 -07:00
wasm	[wasm] emsdk: allow to install emscripten only (#7961)	2021-06-07 09:45:02 -07:00
__init__.py
amd_hipify.py	Explicitly pass cuda stream to thrust function rather than use cuda default stream implicitly (#7414)	2021-04-25 01:18:56 -07:00
build.py	Create python packages for DML (#8061)	2021-06-16 16:59:12 -07:00
clean_docker_image_cache.py
coverage.py
gen_def.py
get_docker_image.py
logger.py
op_registration_utils.py	Update Android AAR packaging pipeline script (#7559)	2021-05-04 11:13:33 -07:00
op_registration_validator.py	Support specifying globally allowed types from build script (#6677)	2021-02-22 14:05:00 -08:00
reduce_op_kernels.py	Support required types when excluding typed registrations (#6871)	2021-03-08 08:22:07 -08:00
requirements.txt	transformers test CI pipeline fix (#8016)	2021-06-11 12:57:52 -07:00
upload_python_package_to_azure_storage.py	to support multiple cuda versions in published onnxruntime-training package (#7468)	2021-04-27 17:15:33 -07:00