tensorflow-1 in docker is crushing over and over

[NofLevi10root]

Every time I'm trying to run the docker.
I get this message:
deeppass-tensorflow-1 | 2022-11-08 15:00:10.067722: I external/org_tensorflow/tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
deeppass-tensorflow-1 | 2022-11-08 15:00:10.075827: I tensorflow_serving/model_servers/server_core.cc:465] Adding/updating models.
deeppass-tensorflow-1 | 2022-11-08 15:00:10.075860: I tensorflow_serving/model_servers/server_core.cc:594] (Re-)adding model: password
deeppass-tensorflow-1 | 2022-11-08 15:00:10.267574: I tensorflow_serving/core/basic_manager.cc:740] Successfully reserved resources to load servable {name: password version: 1}
deeppass-tensorflow-1 | 2022-11-08 15:00:10.267642: I tensorflow_serving/core/loader_harness.cc:66] Approving load for servable version {name: password version: 1}
deeppass-tensorflow-1 | 2022-11-08 15:00:10.267655: I tensorflow_serving/core/loader_harness.cc:74] Loading servable version {name: password version: 1}
deeppass-tensorflow-1 | 2022-11-08 15:00:10.273474: I external/org_tensorflow/tensorflow/cc/saved_model/reader.cc:45] Reading SavedModel from: /models/bilstm_model/1
deeppass-tensorflow-1 | 2022-11-08 15:00:10.393738: I external/org_tensorflow/tensorflow/cc/saved_model/reader.cc:89] Reading meta graph with tags { serve }
deeppass-tensorflow-1 | 2022-11-08 15:00:10.393788: I external/org_tensorflow/tensorflow/cc/saved_model/reader.cc:130] Reading SavedModel debug info (if present) from: /models/bilstm_model/1
deeppass-tensorflow-1 | 2022-11-08 15:00:10.395129: I external/org_tensorflow/tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA
deeppass-tensorflow-1 | To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
deeppass-tensorflow-1 | 2022-11-08 15:00:10.597273: I external/org_tensorflow/tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
deeppass-tensorflow-1 | 2022-11-08 15:00:10.671806: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:229] Restoring SavedModel bundle.
deeppass-tensorflow-1 | terminate called after throwing an instance of 'std::bad_alloc'
deeppass-tensorflow-1 | what(): std::bad_alloc
deeppass-tensorflow-1 | /usr/bin/tf_serving_entrypoint.sh: line 3: 7 Aborted tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=${MODEL_NAME} --model_base_path=${MODEL_BASE_PATH}/${MODEL_NAME} "$@"
deeppass-tensorflow-1 exited with code 134

[Retrospected]

I was facing the same issue but figured this is due to a bug in the tensorflow/serving container also mentioned here: tensorflow/serving#2048

as a workaround for now, you can use an older version of the image by adding the version 2.8.2 tag to the docker-compose.yml

-    image: tensorflow/serving:latest
+    image: tensorflow/serving:2.8.2