Cache a model, rename genai target, fix Windows

.github/workflows/causal_lm_cpp.yml

@@ -30,7 +30,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model openlm-research/open_llama_3b_v2 open_llama_3b_v2
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j
@@ -58,7 +57,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j
@@ -228,7 +226,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model Qwen/Qwen-7B-Chat Qwen-7B-Chat
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j
@@ -256,7 +253,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model Qwen/Qwen1.5-7B-Chat Qwen1.5-7B-Chat
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j
@@ -284,7 +280,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model microsoft/phi-2 phi-2
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j 15
@@ -312,7 +307,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model argilla/notus-7b-v1 notus-7b-v1
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j
@@ -340,7 +334,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model databricks/dolly-v2-3b dolly-v2-3b
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model databricks/dolly-v2-7b dolly-v2-7b
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
@@ -379,7 +372,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j
@@ -424,7 +416,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model microsoft/phi-1_5 phi-1_5
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j 15
@@ -469,7 +460,6 @@ jobs:
           source ./ov/setupvars.sh
           python -m pip install --upgrade-strategy eager -r ./text_generation/causal_lm/cpp/requirements.txt
           python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-          sudo apt-get install libtbb-dev
           optimum-cli export openvino --trust-remote-code --weight-format fp16 --model ikala/redpajama-3b-chat redpajama-3b-chat
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
           cmake --build ./build/ --config Release -j

.github/workflows/genai_package.yml

@@ -9,6 +9,8 @@ jobs:
       matrix:
         build-type: [Release, Debug]
     runs-on: ubuntu-20.04
+    env:
+      CMAKE_BUILD_PARALLEL_LEVEL: null
     steps:
       - uses: actions/checkout@v4
         with:
@@ -19,20 +21,17 @@ jobs:
       - run: mkdir ./ov/
       - run: curl https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.2.0rc1/linux/l_openvino_toolkit_ubuntu20_2024.2.0.dev20240524_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
       - run: sudo ./ov/install_dependencies/install_openvino_dependencies.sh
-      - run: sudo apt-get install libtbb-dev
       - run: source ./ov/setupvars.sh && cmake -DCMAKE_BUILD_TYPE=${{ matrix.build-type }} -S ./ -B ./build/
       - run: source ./ov/setupvars.sh && cmake --build ./build/ --config ${{ matrix.build-type }} --target package -j
       - run: source ./ov/setupvars.sh && cmake --install ./build/ --config ${{ matrix.build-type }} --prefix ov
       - run: ov/samples/cpp/build_samples.sh -i ${{ github.workspace }}/s\ pace
         if: ${{ 'Release' == matrix.build-type }}  # build_samples enforces Release build
-      - run: source ./ov/setupvars.sh && python -m pip install --upgrade-strategy eager -r text_generation/causal_lm/cpp/requirements.txt
-        if: ${{ 'Release' == matrix.build-type }}
+      - run: source ./ov/setupvars.sh && cmake -DCMAKE_BUILD_TYPE=${{ matrix.build-type }} -S ./ov/samples/cpp/ -B ./samples\ build/ && cmake --build ./samples\ build/ --config ${{ matrix.build-type }} -j && cmake --install ./samples\ build/ --config ${{ matrix.build-type }} --component samples_bin --prefix s\ pace
+        if: ${{ 'Release' != matrix.build-type }}
       - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
-        if: ${{ 'Release' == matrix.build-type }}
+      - run: source ./ov/setupvars.sh && python -m pip install --upgrade-strategy eager -r text_generation/causal_lm/cpp/requirements.txt
       - run: source ./ov/setupvars.sh && optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
-        if: ${{ 'Release' == matrix.build-type }}
       - run: source ./ov/setupvars.sh && timeout 50s ${{ github.workspace }}/s\ pace/samples_bin/greedy_causal_lm ./TinyLlama-1.1B-Chat-v1.0/ ""
-        if: ${{ 'Release' == matrix.build-type }}
 
   macos_genai_package:
     strategy:
@@ -68,6 +67,8 @@ jobs:
       matrix:
         build-type: [Release, Debug]
     runs-on: windows-latest
+    env:
+      CMAKE_BUILD_PARALLEL_LEVEL: null
     defaults:
       run:
         shell: cmd
@@ -85,10 +86,10 @@ jobs:
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && cmake --install ./build/ --config ${{ matrix.build-type }} --prefix w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\samples\cpp\build_samples_msvc.bat -i "${{ github.workspace }}/samples_install"
         if: ${{ 'Release' == matrix.build-type }}  # build_samples enforces Release build
-      - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install --upgrade-strategy eager -r text_generation/causal_lm/cpp/requirements.txt
-        if: ${{ 'Release' == matrix.build-type }}
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
         if: ${{ 'Release' == matrix.build-type }}
+      - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install --upgrade-strategy eager -r text_generation/causal_lm/cpp/requirements.txt
+        if: ${{ 'Release' == matrix.build-type }}
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
         if: ${{ 'Release' == matrix.build-type }}
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && "${{ github.workspace }}/samples_install/samples_bin/greedy_causal_lm" .\TinyLlama-1.1B-Chat-v1.0\ ""

.github/workflows/genai_python_lib.yml

@@ -5,10 +5,10 @@ concurrency:
   cancel-in-progress: true
 jobs:
   ubuntu_genai_python_lib:
-    # A tokenizers' dependency fails to compile on ubuntu-20 n CenOS7 env
+    # A tokenizers' dependency fails to compile on ubuntu-20 n CenOS7 env.
     runs-on: ubuntu-22.04
     env:
-      # A tokenizers' dependency fails to compile with Ninja in CenOS7 env
+      # A tokenizers' dependency fails to compile with Ninja in CenOS7 env.
       CMAKE_GENERATOR: Unix Makefiles
       CMAKE_BUILD_PARALLEL_LEVEL: null
     steps:
@@ -19,25 +19,20 @@ jobs:
         with:
           python-version: 3.8
       - run: mkdir ./ov/
-      - run: curl https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.2.0rc1/linux/l_openvino_toolkit_centos7_2024.2.0.dev20240524_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz  # Install CentOS7 instead of Ubuntu to match PyPI distribution ABI
+      # Install CentOS7 instead of Ubuntu to match PyPI distribution ABI
+      - run: curl https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.2.0rc1/linux/l_openvino_toolkit_centos7_2024.2.0.dev20240524_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
       - run: sudo ./ov/install_dependencies/install_openvino_dependencies.sh
       - run: source ./ov/setupvars.sh && cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
       - run: source ./ov/setupvars.sh && cmake --build ./build/ --config Release -j
       # GitHub Actions already provides what is listed in ./requirements-build.txt but the internal
       # build system doesn't. Install ./requirements-build.txt to detect possible conflicts.
-      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./requirements-build.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --verbose
-      - run: source ./ov/setupvars.sh && PYTHONPATH=./build/ python -c "from openvino_genai import LLMPipeline"
+      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./requirements-build.txt -r ./tests/python_tests/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+      # The tests can convert the model themselves, but underlying OpenVINO silently saves empty .xml if there's no space.
+      - run: source ./ov/setupvars.sh && optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
+      # --exitfirst to exit instantly on first error because tests are slow and produce lots of logs slowing down GitHub Actions logs view.
+      - run: source ./ov/setupvars.sh && PYTHONPATH=./build/:$PYTHONPATH python -m pytest ./tests/python_tests/test_generate_api.py --exitfirst -m precommit
       - run: source ./ov/setupvars.sh && python -m pip install . --config-settings=build-dir="build" --verbose
-      - run: python -c "from openvino_genai import LLMPipeline"
-      - name: GenAI Python API tests
-        run: |
-          cd ./tests/python_tests/
-          python -m pip install -r requirements.txt
-          models=$(python list_test_models.py)
-          echo "$models" | while read -r model_name model_path; do
-              optimum-cli export openvino --trust-remote-code --weight-format fp16 --model "$model_name" "$model_path"
-          done
-          GENAI_BUILD_DIR=../../build python -m pytest test_generate_api.py -v -m precommit
+      - run: python -m pytest ./tests/python_tests/test_generate_api.py --exitfirst -m precommit
 
   macos_genai_python_lib:
     runs-on: macos-12
@@ -89,9 +84,10 @@ jobs:
       - run: unzip ov.zip
       # GitHub Actions already provides what is listed in ./requirements-build.txt but the internal
       # build system doesn't. Install ./requirements-build.txt to detect possible conflicts.
-      - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./requirements-build.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --verbose
-      - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install . --verbose
-      - run: python -c "from openvino_genai import LLMPipeline"
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
       - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && cmake --build ./build/ --config Release -j
-      - run: set "PYTHONPATH=./build/" && call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -c "from openvino_genai import LLMPipeline"  # cmd evaluates variables in a different way. Setting PYTHONPATH before setupvars.bat instead of doing that after solves that.
+      - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./requirements-build.txt -r ./tests/python_tests/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+      # cmd evaluates variables in a different way. Setting PYTHONPATH before setupvars.bat instead of doing that after solves that.
+      - run: set "PYTHONPATH=./build/" && call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pytest ./tests/python_tests/test_generate_api.py --exitfirst -m precommit
+      - run: call w_openvino_toolkit_windows_2024.2.0.dev20240524_x86_64\setupvars.bat && python -m pip install . --config-settings=build-dir="build" --verbose
+      - run: python -m pytest ./tests/python_tests/test_generate_api.py --exitfirst -m precommit

pyproject.toml

@@ -20,8 +20,9 @@ dependencies = [
 ]
 
 [tool.scikit-build]
-cmake.source-dir = "./"
 cmake.build-type = "Release"
+cmake.source-dir = "./"
+cmake.targets = ["py_generate_pipeline"]  # Adding genai would trigger a Release build and Debug build after it. py_generate_pipeline depends on genai and genai will be built anyway. It's not been investigated why both build types are triggered.
 install.components = ["wheel_genai"]
 sdist.cmake = true
 wheel.packages = ["src/python/openvino_genai"]

src/cpp/CMakeLists.txt

@@ -39,7 +39,7 @@ ov_genai_build_jinja2cpp()
 
 file(GLOB SOURCE_FILES "${CMAKE_CURRENT_SOURCE_DIR}/src/*.cpp")
 
-set(TARGET_NAME genai)
+set(TARGET_NAME openvino_genai)
 add_library(${TARGET_NAME} SHARED ${SOURCE_FILES})
 add_library(openvino::genai ALIAS ${TARGET_NAME})
 
@@ -53,7 +53,7 @@ target_compile_features(${TARGET_NAME} PUBLIC cxx_std_17)
 # Extract two last digits from CMAKE_PROJECT_VERSION_MAJOR because SOVERSION can only contain up to 4 symbols.
 string(REGEX MATCH [=[[0-9][0-9]$]=] MAJOR_SUFFIX ${CMAKE_PROJECT_VERSION_MAJOR})
 set_target_properties(${TARGET_NAME} PROPERTIES
-    OUTPUT_NAME openvino_genai
+    EXPORT_NAME genai
     VERSION ${CMAKE_PROJECT_VERSION}
     SOVERSION ${MAJOR_SUFFIX}${CMAKE_PROJECT_VERSION_MINOR}${CMAKE_PROJECT_VERSION_PATCH}
     ARCHIVE_OUTPUT_DIRECTORY "$<1:${CMAKE_BINARY_DIR}/openvino_genai/>"

src/cpp/OpenVINOGenAIConfig.cmake.in

@@ -3,8 +3,8 @@
 include(CMakeFindDependencyMacro)
 find_dependency(OpenVINO COMPONENTS Runtime)
 
-if(NOT TARGET genai)
+if(NOT TARGET openvino_genai)
     include("${CMAKE_CURRENT_LIST_DIR}/OpenVINOGenAITargets.cmake")
 endif()
 
-check_required_components(openvino_genai)
+check_required_components(OpenVINOGenAI)

src/cpp/include/openvino/genai/llm_pipeline.hpp

@@ -209,8 +209,8 @@ class OPENVINO_GENAI_EXPORTS LLMPipeline {
     std::unique_ptr<LLMPipelineImpl> m_pimpl;
 };
 
-std::pair<std::string, Any> streamer(StreamerVariant func);
-std::pair<std::string, Any> generation_config(const GenerationConfig& config);
+OPENVINO_GENAI_EXPORTS std::pair<std::string, Any> streamer(StreamerVariant func);
+OPENVINO_GENAI_EXPORTS std::pair<std::string, Any> generation_config(const GenerationConfig& config);
 
 }  // namespace genai
 }  // namespace ov

src/cpp/include/openvino/genai/visibility.hpp

@@ -1,10 +1,12 @@
 // Copyright (C) 2023-2024 Intel Corporation
 // SPDX-License-Identifier: Apache-2.0
 
+#pragma once
+
 #include "openvino/core/visibility.hpp"
 
-#ifdef genai_EXPORTS
+#ifdef openvino_genai_EXPORTS
 #    define OPENVINO_GENAI_EXPORTS OPENVINO_CORE_EXPORTS
 #else
 #    define OPENVINO_GENAI_EXPORTS OPENVINO_CORE_IMPORTS
-#endif  // genai_EXPORTS
+#endif  // openvino_genai_EXPORTS