diff --git a/ci/build_test_OnCommit.groovy b/ci/build_test_OnCommit.groovy index 0435645689..5573d55ce6 100644 --- a/ci/build_test_OnCommit.groovy +++ b/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" diff --git a/demos/age_gender_recognition/python/README.md b/demos/age_gender_recognition/python/README.md index e3d0929e00..b6cd1d2254 100644 --- a/demos/age_gender_recognition/python/README.md +++ b/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 diff --git a/demos/common/python/requirements.txt b/demos/common/python/requirements.txt index 427c7cae26..fe0f1d0ae4 100644 --- a/demos/common/python/requirements.txt +++ b/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 diff --git a/demos/face_detection/python/README.md b/demos/face_detection/python/README.md index b51ac388da..c930c64b0c 100644 --- a/demos/face_detection/python/README.md +++ b/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: diff --git a/demos/universal-sentence-encoder/README.md b/demos/universal-sentence-encoder/README.md index 391b17d3f3..04642f1147 100644 --- a/demos/universal-sentence-encoder/README.md +++ b/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 diff --git a/docs/image_generation/reference.md b/docs/image_generation/reference.md index f87927b814..e0a07ea4e2 100644 --- a/docs/image_generation/reference.md +++ b/docs/image_generation/reference.md @@ -223,7 +223,7 @@ Each individual adapter can optionally specify a default alpha weight by appendi The alpha value controls how strongly the adapter influences generation (default: `1.0`). Examples: -```bash +```text # Linux - adapter with alpha 0.6 --source_loras="pokemon=/models/loras/pokemon.safetensors:0.6" @@ -240,11 +240,14 @@ The alpha value controls how strongly the adapter influences generation (default **Example:** ```bash -ovms --rest_port 8000 \ +mkdir -p ${HOME}/models +docker run -d -p 8000:8000 --rm --user $(id -u):$(id -g) -v ${HOME}/models:/models:rw \ + openvino/model_server:latest \ + --rest_port 8000 \ --model_repository_path /models/ \ --task image_generation \ --source_model stabilityai/stable-diffusion-xl-base-1.0 \ - --source_loras "xray=DoctorDiffusion/doctor-diffusion-s-xray-xl-lora@DD-xray-v1.safetensors,ukiyo=KappaNeuro/ukiyo-e-art@Ukiyo-e Art.safetensors,vector=DoctorDiffusion/doctor-diffusion-s-controllable-vector-art-xl-lora@DD-vector-v2.safetensors" + --source_loras "xray=DoctorDiffusion/doctor-diffusion-s-xray-xl-lora@DD-xray-v1.safetensors,ukiyo=KappaNeuro/ukiyo-e-art@Ukiyo-e%20Art.safetensors,vector=DoctorDiffusion/doctor-diffusion-s-controllable-vector-art-xl-lora@DD-vector-v2.safetensors" ``` > **Important:** LoRA adapters must be compatible with the base model architecture. For example, SDXL adapters can only be used with an SDXL base model. diff --git a/docs/model_server_rest_api_tokenizer.md b/docs/model_server_rest_api_tokenizer.md index 6319c051a8..cbc7d744c8 100644 --- a/docs/model_server_rest_api_tokenizer.md +++ b/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)