You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When serving a GPFlow saved_model in TFServing 2.9+, the model server crashes
2022-09-19 09:50:19.941042: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:229] Restoring SavedModel bundle.
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
/usr/bin/tf_serving_entrypoint.sh: line 3: 7 Aborted (core dumped) tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=${MODEL_NAME} --model_base_path=${MODEL_BASE_PATH}/${MODEL_NAME} "$@"
This is related to the slice() operation inside the Kernel class. I just filled out the bug report also in the tensorflow/serving repository: tensorflow/serving#2061
I would like to be able to serve the model on TFServing. Possibly rewriting the slice operation could work.
System information
GPflow version: 2.5.2
GPflow installed from: pypi
TensorFlow version: 2.9.2
Python version 3.8
Operating system Windows
Additional context
It seems like a regression from TF 2.9, where they dropped support to this slice() operation (for TFServing).
I've already created an issue on tensorflow/serving github page to see if this is the case or not. If so, just ignore this issue...
The text was updated successfully, but these errors were encountered:
I'm sorry, but I have no experience with TFServing whatsoever so I don't know how I'd debug this. However GPflow is a Open Source project, and if you send me a PR with a fix I'd happily review it.
Bug
When serving a GPFlow saved_model in TFServing 2.9+, the model server crashes
This is related to the slice() operation inside the Kernel class. I just filled out the bug report also in the tensorflow/serving repository: tensorflow/serving#2061
To reproduce
Minimal, reproducible example
This does not work:
While this one works fine:
The only difference is
presliced=True
that will skip the operationx[..., slice]
that will crash the model server.To test, I run the tensorflow serving instance with the following command:
And with the following models.config:
Expected behavior
I would like to be able to serve the model on TFServing. Possibly rewriting the slice operation could work.
System information
Additional context
It seems like a regression from TF 2.9, where they dropped support to this slice() operation (for TFServing).
I've already created an issue on tensorflow/serving github page to see if this is the case or not. If so, just ignore this issue...
The text was updated successfully, but these errors were encountered: