update_groovy_doc_on_commit

ci/build_test_OnCommit.groovy

@@ -340,7 +340,7 @@ pipeline {
                       sh "pwd"
                       def pwd = sh(returnStdout:true, script: "pwd").strip()
                       def ovms_c_repo_path = sh(returnStdout:true, script: "cd .. && pwd").strip()
-                      def test_doc_files_str = test_doc_files_linux.split('\n').join(' or ')
+                      def test_doc_files_str = test_doc_files_linux.split('\n').collect { 'U-' + it }.join(' or ')
                       sh "make create-venv && rm -f tests/functional && ln -s ${pwd}/../tests/functional tests/functional"
                       def cmd_venv_activate = ". .venv/bin/activate"
                       def cmd_export = "export TT_OVMS_C_REPO_PATH=../ && export TT_RUN_REGRESSION_TESTS=True && export TT_REGRESSION_WEEKLY_TESTS=True && export TT_TARGET_DEVICE=CPU,GPU,NPU && export TT_ENABLE_UAT_TESTS=True && export TT_ENABLE_SMOKE_TESTS=False && export TT_OVMS_C_REPO_PATH=${ovms_c_repo_path} && export TT_LOGGING_LEVEL_OVMS=DEBUG && export TT_WAIT_FOR_MESSAGES_TIMEOUT=1500 && export CORE_BRANCH=${env.CHANGE_BRANCH ?: 'main'}"
@@ -403,7 +403,7 @@ pipeline {
                   script {
                     dir ('documentation_tests') {
                       checkout scmGit(branches: [[name: validation_branch]], userRemoteConfigs: [[credentialsId: 'workflow-lab', url: 'https://github.com/intel-innersource/frameworks.ai.openvino.model-server.tests.git']])
-                      def test_doc_files_str = test_doc_files_windows.split('\n').join(' or ')
+                      def test_doc_files_str = test_doc_files_windows.split('\n').collect { 'U-' + it }.join(' or ')
                       def current_path = bat(returnStdout: true, script: 'cd').trim().split('\n').last().trim()
                       def ovms_c_repo_path = bat(returnStdout: true, script: 'cd .. && cd').trim().split('\n').last().trim()
                       def cmd_link_ovms = "(if exist ${current_path}\\tests\\functional rmdir ${current_path}\\tests\\functional) && mklink /D ${current_path}\\tests\\functional ${ovms_c_repo_path}\\tests\\functional"

demos/age_gender_recognition/python/README.md

@@ -30,7 +30,7 @@ Assuming you have unpacked model server package, make sure to:
 
 as mentioned in [deployment guide](../../../docs/deploying_server_baremetal.md), in every new shell that will start OpenVINO Model Server.
 ```bat
-ovms --model_path model --model_name age_gender --port 9000 --rest_port 8000
+ovms --model_path model --model_name age_gender --port 9000 --rest_port 8000 --target_device CPU
 ```
 :::
 #### Requesting the Service

demos/c_api_minimal_app/Makefile

@@ -25,13 +25,13 @@ BASE_OS ?= ubuntu24
 
 ifeq ($(BASE_OS),ubuntu24)
   BASE_OS_TAG_UBUNTU ?= 24.04
-  PACKAGE_URL ?="https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_ubuntu24_2026.2.0_python_off.tar.gz"
+  PACKAGE_URL ?="https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_ubuntu24_2026.3.0_python_off.tar.gz"
   BASE_IMAGE ?= ubuntu:$(BASE_OS_TAG_UBUNTU)
   DIST_OS=ubuntu
 endif
 ifeq ($(BASE_OS),redhat)
   BASE_OS_TAG_REDHAT ?= 9.6
-  PACKAGE_URL ="https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_redhat_2026.2.0_python_off.tar.gz"
+  PACKAGE_URL ="https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_redhat_2026.3.0_python_off.tar.gz"
   BASE_IMAGE ?= registry.access.redhat.com/ubi9/ubi:$(BASE_OS_TAG_REDHAT)
   DIST_OS=redhat
 endif

demos/common/python/requirements.txt

@@ -1,4 +1,5 @@
 futures==3.1.1
 opencv-python>=4.8.1.78
+requests==2.34.2
 tritonclient[grpc]
 numpy<2.0.0

demos/face_detection/python/README.md

@@ -91,7 +91,7 @@ Assuming you have unpacked model server package, make sure to:
 
 as mentioned in [deployment guide](../../../docs/deploying_server_baremetal.md), in every new shell that will start OpenVINO Model Server.
 ```bat
-ovms --model_path model --model_name face-detection --port 9000  --shape auto
+ovms --model_path model --model_name face-detection --port 9000  --shape auto --target_device CPU
 ```
 :::
 Run the client:

demos/universal-sentence-encoder/README.md

@@ -57,7 +57,7 @@ on every shell that will start OpenVINO Model Server.
 
 And start Model Server using the following command:
 ```bat
-ovms --model_name usem --model_path universal-sentence-encoder-multilingual/ --plugin_config "{\"NUM_STREAMS\": 1}" --port 9000 --rest_port 8000
+ovms --model_name usem --model_path universal-sentence-encoder-multilingual/ --plugin_config "{\"NUM_STREAMS\": 1}" --port 9000 --rest_port 8000 --target_device CPU
 ```
 
 ## Send string data as inference request

docs/deploying_server_baremetal.md

@@ -15,13 +15,13 @@ You can download model server package in two configurations. One with Python sup
 :sync: ubuntu-22-04
 Download precompiled package (without python):
 ```{code} sh
-wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_ubuntu22_2026.2.0_python_off.tar.gz
-tar -xzvf ovms_ubuntu22_2026.2.0_python_off.tar.gz
+wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_ubuntu22_2026.3.0_python_off.tar.gz
+tar -xzvf ovms_ubuntu22_2026.3.0_python_off.tar.gz
 ```
 or precompiled package (with python):
 ```{code} sh
-wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_ubuntu22_2026.2.0_python_on.tar.gz
-tar -xzvf ovms_ubuntu22_2026.2.0_python_on.tar.gz
+wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_ubuntu22_2026.3.0_python_on.tar.gz
+tar -xzvf ovms_ubuntu22_2026.3.0_python_on.tar.gz
 ```
 Install required libraries:
 ```{code} sh
@@ -50,13 +50,13 @@ Model server version with Python is shipped with those packages and new installa
 :sync: ubuntu-24-04
 Download precompiled package (without python):
 ```{code} sh
-wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_ubuntu24_2026.2.0_python_off.tar.gz
-tar -xzvf ovms_ubuntu24_2026.2.0_python_off.tar.gz
+wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_ubuntu24_2026.3.0_python_off.tar.gz
+tar -xzvf ovms_ubuntu24_2026.3.0_python_off.tar.gz
 ```
 or precompiled package (with python):
 ```{code} sh
-wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_ubuntu24_2026.2.0_python_on.tar.gz
-tar -xzvf ovms_ubuntu24_2026.2.0_python_on.tar.gz
+wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_ubuntu24_2026.3.0_python_on.tar.gz
+tar -xzvf ovms_ubuntu24_2026.3.0_python_on.tar.gz
 ```
 Install required libraries:
 ```{code} sh
@@ -85,13 +85,13 @@ Model server version with Python is shipped with those packages and new installa
 :sync: rhel-9.6
 Download precompiled package (without python):
 ```{code} sh
-wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_redhat_2026.2.0_python_off.tar.gz
-tar -xzvf ovms_redhat_2026.2.0_python_off.tar.gz
+wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_redhat_2026.3.0_python_off.tar.gz
+tar -xzvf ovms_redhat_2026.3.0_python_off.tar.gz
 ```
 or precompiled package (with python):
 ```{code} sh
-wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_redhat_2026.2.0_python_on.tar.gz
-tar -xzvf ovms_redhat_2026.2.0_python_on.tar.gz
+wget https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_redhat_2026.3.0_python_on.tar.gz
+tar -xzvf ovms_redhat_2026.3.0_python_on.tar.gz
 ```
 Install required libraries:
 ```{code} sh
@@ -124,14 +124,14 @@ Make sure you have [Microsoft Visual C++ Redistributable](https://aka.ms/vs/17/r
 Download and unpack model server archive for Windows(with python):
 
 ```bat
-curl -L https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_windows_2026.2.0_python_on.zip -o ovms.zip
+curl -L https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_windows_2026.3.0_python_on.zip -o ovms.zip
 tar -xf ovms.zip
 ```
 
 or archive without python:
 
 ```bat
-curl -L https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_windows_2026.2.0_python_off.zip -o ovms.zip
+curl -L https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_windows_2026.3.0_python_off.zip -o ovms.zip
 tar -xf ovms.zip
 ```
 

docs/model_server_rest_api_tokenizer.md

@@ -6,7 +6,7 @@ Example usage:
 
 Deploy OVMS with LLM, VLM or embedding model:
 ```bash
-mkdir models
+mkdir -p ${HOME}/models
 # in case GPU is available
 export GPU_ARGS=$(if ls /dev/dri/render* >/dev/null 2>&1; then echo "--device /dev/dri --group-add $(stat -c '%g' /dev/dri/render* | head -n1)"; fi)
 

docs/pull_optimum_cli.md

@@ -15,7 +15,7 @@ mkdir models
 ## Add optimum-cli to OVMS installation on windows
 
 ```bat
-curl -L https://github.com/openvinotoolkit/model_server/releases/download/v2026.2/ovms_windows_2026.2.0_python_on.zip -o ovms.zip
+curl -L https://github.com/openvinotoolkit/model_server/releases/download/v2026.3/ovms_windows_2026.3.0_python_on.zip -o ovms.zip
 tar -xf ovms.zip
 ovms\setupvars.bat
 ovms\python\python -m pip install -r https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/main/demos/common/export_models/requirements.txt

tests/functional/config.py

@@ -241,7 +241,7 @@ def get_uses_mapping():
 server_address = os.environ.get("TT_SERVER_ADDRESS", "localhost")
 
 """ TT_RESOURCE_MONITOR_ENABLED - Dump ovms container resource statistics once per second """
-resource_monitor_enabled = get_bool("TT_RESOURCE_MONITOR_ENABLED", True)
+resource_monitor_enabled = get_bool("TT_RESOURCE_MONITOR_ENABLED", False)
 
 """ TT_TEST_TEMP_DIR - directory path where all temporary files are stored, default is not set """
 test_temp_dir = os.environ.get("TT_TEST_TEMP_DIR", None)