You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/04/09 01:42:44 UTC
[GitHub] [tvm] MadFunMaker opened a new issue #7812: TensorRT unit test fails
MadFunMaker opened a new issue #7812:
URL: https://github.com/apache/tvm/issues/7812
I found that the most recent TVM version fails the unit test of TensorRT. I tried the following command for that:
`TVM_FFI=ctypes python -m pytest -v tests/python/contrib/test_tensorrt.py`
From the following error message, I suspect this is because of the module name change from GraphRuntime to GraphExecutor.
`enabled targets: cuda; llvm; nvptx; llvm -device=arm_cpu
pytest marker:
============================= test session starts ==============================
platform linux -- Python 3.8.5, pytest-6.2.2, py-1.10.0, pluggy-0.13.1 -- /opt/anaconda3/bin/python
cachedir: .pytest_cache
rootdir: /home/byungsoj/temp_local/tvm, configfile: pytest.ini
collecting ... collected 0 items / 1 error
==================================== ERRORS ====================================
____________ ERROR collecting tests/python/contrib/test_tensorrt.py ____________
ImportError while importing test module '/home/byungsoj/temp_local/tvm/tests/python/contrib/test_tensorrt.py'.
Hint: make sure your test modules/packages have valid Python names.
Traceback:
/opt/anaconda3/lib/python3.8/importlib/__init__.py:127: in import_module
return _bootstrap._gcd_import(name[level:], package, level)
tests/python/contrib/test_tensorrt.py:27: in <module>
from tvm.contrib import graph_executor, utils
E ImportError: cannot import name 'graph_executor' from 'tvm.contrib' (/opt/tvm/python/tvm/contrib/__init__.py)
=============================== warnings summary ===============================
<frozen importlib._bootstrap>:219
<frozen importlib._bootstrap>:219: RuntimeWarning: numpy.ufunc size changed, may indicate binary incompatibility. Expected 192 from C header, got 216 from PyObject
-- Docs: https://docs.pytest.org/en/stable/warnings.html
=========================== short test summary info ============================
ERROR tests/python/contrib/test_tensorrt.py
!!!!!!!!!!!!!!!!!!!! Interrupted: 1 error during collection !!!!!!!!!!!!!!!!!!!!
========================= 1 warning, 1 error in 0.59s ==========================
`
@areusch
--
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:
users@infra.apache.org
[GitHub] [tvm] comaniac commented on issue #7812: TensorRT unit test fails
Posted by GitBox <gi...@apache.org>.
comaniac commented on issue #7812:
URL: https://github.com/apache/tvm/issues/7812#issuecomment-816344862
The test passed the CI so it should be fine. Your error shows `ImportError: cannot import name 'graph_executor' from 'tvm.contrib' (/opt/tvm/python/tvm/contrib/init.py)`. Since graph_runtime recently is renamed to graph_executor, is it possible that you are using the old version with updated test?
--
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:
users@infra.apache.org
[GitHub] [tvm] MadFunMaker closed issue #7812: TensorRT unit test fails
Posted by GitBox <gi...@apache.org>.
MadFunMaker closed issue #7812:
URL: https://github.com/apache/tvm/issues/7812
--
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:
users@infra.apache.org
[GitHub] [tvm] MadFunMaker commented on issue #7812: TensorRT unit test fails
Posted by GitBox <gi...@apache.org>.
MadFunMaker commented on issue #7812:
URL: https://github.com/apache/tvm/issues/7812#issuecomment-816745543
@comaniac Thank you for pointing that out! That was my bad. But. I still get the seg fault as I updated above.
--
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:
users@infra.apache.org