To reproduce:
# bazel run -c opt lingvo/jax:main -- --model=lm.ptb.PTBCharTransformerSmallSgd --job_log_dir=/tmp/jax_log_dir/exp01 --alsologtostderr
...
2022-03-24 17:46:18.859227: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
Traceback (most recent call last):
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/ops/__init__.py", line 22, in <module>
from lingvo.core.ops import gen_x_ops # pylint: disable=g-import-not-at-top
ImportError: cannot import name 'gen_x_ops' from 'lingvo.core.ops' (/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/ops/__init__.py)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/jax/main.py", line 36, in <module>
from lingvo.jax import eval as eval_lib
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/jax/eval.py", line 29, in <module>
from lingvo.jax import base_input
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/jax/base_input.py", line 23, in <module>
from lingvo.core import datasource
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/datasource.py", line 33, in <module>
from lingvo.core import base_layer
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/base_layer.py", line 27, in <module>
from lingvo.core import py_utils
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/py_utils.py", line 43, in <module>
from lingvo.core import ops
File "/root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/ops/__init__.py", line 25, in <module>
tf.resource_loader.get_path_to_datafile('x_ops.so'))
File "/usr/local/lib/python3.7/site-packages/tensorflow/python/framework/load_library.py", line 54, in load_op_library
lib_handle = py_tf.TF_LoadLibrary(library_filename)
tensorflow.python.framework.errors_impl.NotFoundError: /root/.cache/bazel/_bazel_root/17eb95f0bc03547f4f1319e61997e114/execroot/__main__/bazel-out/k8-opt/bin/lingvo/jax/main.runfiles/__main__/lingvo/core/ops/x_ops.so: undefined symbol: _ZNK10tensorflow6Status14GetAllPayloadsEv
To reproduce: