Merge releases/2024/3 into master (#666)

Co-authored-by: Alina Kladieva <[email protected]> Co-authored-by: Anastasiia Pnevskaia <[email protected]> Co-authored-by: Nikita Malinin <[email protected]> Co-authored-by: Yaroslav Tarkan <[email protected]> Co-authored-by: Anatoliy Talamanov <[email protected]> Co-authored-by: Pavel Esir <[email protected]> Co-authored-by: Miłosz Żeglarski <[email protected]> Co-authored-by: Alexander Suvorov <[email protected]> Co-authored-by: Xiake Sun <[email protected]>
openvinotoolkit · Jul 23, 2024 · c86fd77 · c86fd77
1 parent 5d21486
commit c86fd77
Show file tree

Hide file tree

Showing 27 changed files with 212 additions and 101 deletions.
diff --git a/.github/workflows/causal_lm_cpp.yml b/.github/workflows/causal_lm_cpp.yml
diff --git a/.github/workflows/genai_package.yml b/.github/workflows/genai_package.yml
@@ -5,9 +5,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.ref_name }}
   cancel-in-progress: true
 env:
-  l_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.3.0-15945-a349dc82f9a/l_openvino_toolkit_ubuntu20_2024.3.0.dev20240708_x86_64.tgz
-  m_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.3.0-15945-a349dc82f9a/m_openvino_toolkit_macos_12_6_2024.3.0.dev20240708_x86_64.tgz
-  w_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.3.0-15945-a349dc82f9a/w_openvino_toolkit_windows_2024.3.0.dev20240708_x86_64.zip
+  l_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.3.0rc1/linux/l_openvino_toolkit_ubuntu20_2024.3.0.dev20240711_x86_64.tgz
+  m_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.3.0rc1/macos/m_openvino_toolkit_macos_12_6_2024.3.0.dev20240711_x86_64.tgz
+  w_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.3.0rc1/windows/w_openvino_toolkit_windows_2024.3.0.dev20240711_x86_64.zip
 jobs:
   ubuntu_genai_package:
     strategy:
@@ -28,8 +28,8 @@ jobs:
       - run: sudo ./ov/install_dependencies/install_openvino_dependencies.sh
       - 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 && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-      - run: source ./ov/setupvars.sh && python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
+      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+      - run: source ./ov/setupvars.sh && python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
       - run: source ./ov/setupvars.sh && optimum-cli export openvino --trust-remote-code --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
       - run: source ./ov/setupvars.sh && cmake --install ./build/ --config ${{ matrix.build-type }} --prefix ov
       - run: ov/samples/cpp/build_samples.sh -i ${{ github.workspace }}/s\ pace
@@ -57,8 +57,8 @@ jobs:
       - run: brew install coreutils scons
       - run: source ./ov/setupvars.sh && cmake -DCMAKE_BUILD_TYPE=${{ 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 && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-      - run: source ./ov/setupvars.sh && python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
+      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+      - run: source ./ov/setupvars.sh && python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
       - run: source ./ov/setupvars.sh && optimum-cli export openvino --trust-remote-code --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
       - run: source ./ov/setupvars.sh && cmake --install ./build/ --config ${{ matrix.build-type }} --prefix ov
       - run: ov/samples/cpp/build_samples.sh -i ${{ github.workspace }}/s\ pace
@@ -100,8 +100,8 @@ jobs:
         shell: bash
       - run: call ov\setupvars.bat && cmake -DCMAKE_BUILD_TYPE=${{ matrix.build-type }} -S ./ -B ./build/
       - run: call ov\setupvars.bat && cmake --build ./build/ --config ${{ matrix.build-type }} --target package -j
-      - run: call ov\setupvars.bat && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-      - run: call ov\setupvars.bat && python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
+      - run: call ov\setupvars.bat && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+      - run: call ov\setupvars.bat && python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
       - run: call ov\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
       - run: call ov\setupvars.bat && cmake --install ./build/ --config ${{ matrix.build-type }} --prefix ov
       - run: call ov\samples\cpp\build_samples_msvc.bat -i "${{ github.workspace }}/samples_install"

diff --git a/.github/workflows/genai_python_lib.yml b/.github/workflows/genai_python_lib.yml
@@ -5,9 +5,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.ref_name }}
   cancel-in-progress: true
 env:
-  l_ov_centos_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.3.0-15945-a349dc82f9a/l_openvino_toolkit_centos7_2024.3.0.dev20240708_x86_64.tgz
-  m_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.3.0-15945-a349dc82f9a/m_openvino_toolkit_macos_12_6_2024.3.0.dev20240708_x86_64.tgz
-  w_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.3.0-15945-a349dc82f9a/w_openvino_toolkit_windows_2024.3.0.dev20240708_x86_64.zip
+  l_ov_centos_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.3.0rc1/linux/l_openvino_toolkit_centos7_2024.3.0.dev20240711_x86_64.tgz
+  m_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.3.0rc1/macos/m_openvino_toolkit_macos_12_6_2024.3.0.dev20240711_x86_64.tgz
+  w_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/pre-release/2024.3.0rc1/windows/w_openvino_toolkit_windows_2024.3.0.dev20240711_x86_64.zip
 jobs:
   ubuntu_genai_python_lib:
     # A tokenizers' dependency fails to compile on ubuntu-20 n CenOS7 env.
@@ -29,7 +29,7 @@ jobs:
       - 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
-      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly --upgrade-strategy eager
+      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --upgrade-strategy eager
       - run: source ./ov/setupvars.sh && PYTHONPATH=./build/:$PYTHONPATH python -m pytest ./tests/python_tests/
       - run: source ./ov/setupvars.sh && python -m pip install . --verbose
       - run: python -m pytest ./tests/python_tests/
@@ -52,7 +52,7 @@ jobs:
       - run: brew install coreutils scons
       - run: source ./ov/setupvars.sh && cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
       - run: source ./ov/setupvars.sh && cmake --build ./build/ --config Release -j
-      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly --upgrade-strategy eager
+      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --upgrade-strategy eager
       - run: source ./ov/setupvars.sh && PYTHONPATH=./build/:$PYTHONPATH python -m pytest ./tests/python_tests/
       - run: source ./ov/setupvars.sh && python -m pip install . --verbose
       - run: python -c "from openvino_genai import LLMPipeline"
@@ -79,12 +79,9 @@ jobs:
           unzip -d ov ov.zip
           dirs=(ov/*) && mv ov/*/* ov && rmdir "${dirs[@]}"
         shell: bash
-      - name: Install dependencies and build
-        run: |
-          call .\ov\setupvars.bat
-          python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly --upgrade-strategy eager
-          cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
-          cmake --build ./build/ --config Release -j
+      - run: call ./ov/setupvars.bat && cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
+      - run: call ./ov/setupvars.bat && cmake --build ./build/ --config Release -j
+      - run: call ./ov/setupvars.bat && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --upgrade-strategy eager
       # cmd evaluates variables in a different way. Setting PYTHONPATH before setupvars.bat instead of doing that after solves that.
       - run: set "PYTHONPATH=./build/" && call ./ov/setupvars.bat && python -m pytest ./tests/python_tests/
       - run: call ./ov/setupvars.bat && python -m pip install . --verbose

diff --git a/.github/workflows/lcm_dreamshaper_cpp.yml b/.github/workflows/lcm_dreamshaper_cpp.yml
@@ -50,8 +50,8 @@ jobs:
         working-directory: ${{ env.working_directory }}
         run: |
           conda activate openvino_lcm_cpp
-          python -m pip install ../../../thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-          python -m pip install -r ../../requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
+          python -m pip install ../../../thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+          python -m pip install -r ../../requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
           
       - name: Download and convert model and tokenizer
         working-directory: ${{ env.working_directory }}
@@ -95,8 +95,8 @@ jobs:
         working-directory: ${{ env.working_directory }}
         run: |
           conda activate openvino_lcm_cpp
-          python -m pip install ../../../thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-          python -m pip install -r ../../requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
+          python -m pip install ../../../thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+          python -m pip install -r ../../requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
 
       - name: Download and convert model and tokenizer
         working-directory: ${{ env.working_directory }}

diff --git a/.github/workflows/stable_diffusion_1_5_cpp.yml b/.github/workflows/stable_diffusion_1_5_cpp.yml
@@ -49,8 +49,8 @@ jobs:
         working-directory: ${{ env.working_directory }}
         run: |
           conda activate openvino_sd_cpp
-          python -m pip install ../../../thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-          python -m pip install -r ../../requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
+          python -m pip install ../../../thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
+          python -m pip install -r ../../requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release
 
       - name: Download and convert model and tokenizer
         working-directory: ${{ env.working_directory }}

diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -57,11 +57,27 @@ if(ENABLE_PYTHON)
     endif()
 endif()
 
+if(ENABLE_PYTHON)
+    # the following two calls are required for cross-compilation
+    if(OpenVINODeveloperPackage_DIR)
+        ov_find_python3(REQUIRED)
+        ov_detect_python_module_extension()
+    else()
+        if(CMAKE_VERSION VERSION_GREATER_EQUAL 3.18)
+            find_package(Python3 REQUIRED COMPONENTS Interpreter Development.Module)
+        else()
+            find_package(Python3 REQUIRED COMPONENTS Interpreter Development)
+        endif()
+    endif()
+endif()
+
 add_subdirectory(thirdparty)
 add_subdirectory(src)
 add_subdirectory(samples)
 add_subdirectory(tests/cpp)
 
+install(FILES LICENSE DESTINATION docs/licensing COMPONENT licensing_genai RENAME LICENSE-GENAI)
+install(FILES third-party-programs.txt DESTINATION docs/licensing COMPONENT licensing_genai RENAME third-party-programs-genai.txt)
 install(FILES LICENSE DESTINATION docs/licensing COMPONENT licensing_genai RENAME LICENSE-GENAI)
 install(FILES third-party-programs.txt DESTINATION docs/licensing COMPONENT licensing_genai RENAME third-party-programs-genai.txt)
 set(CPACK_ARCHIVE_COMPONENT_INSTALL ON)

diff --git a/samples/cpp/beam_search_causal_lm/README.md b/samples/cpp/beam_search_causal_lm/README.md
@@ -1,4 +1,4 @@
-# Text generation C++ sample that supports most popular models like LLaMA 2
+# Text generation C++ sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. It's only possible to change the device for inference to a differnt one, GPU for example, from the command line interface. The sample fearures `ov::genai::LLMPipeline` and configures it to use multiple beam grops. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

diff --git a/samples/cpp/chat_sample/README.md b/samples/cpp/chat_sample/README.md
@@ -1,4 +1,4 @@
-# C++ chat_sample that supports most popular models like LLaMA 2
+# C++ chat_sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it for the chat scenario. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

diff --git a/samples/cpp/greedy_causal_lm/README.md b/samples/cpp/greedy_causal_lm/README.md
@@ -1,4 +1,4 @@
-# Text generation C++ greedy_causal_lm that supports most popular models like LLaMA 2
+# Text generation C++ greedy_causal_lm that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it to run the simplest deterministic greedy sampling algorithm. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

diff --git a/samples/cpp/multinomial_causal_lm/CMakeLists.txt b/samples/cpp/multinomial_causal_lm/CMakeLists.txt
@@ -11,7 +11,7 @@ set_target_properties(multinomial_causal_lm PROPERTIES
     COMPILE_PDB_NAME multinomial_causal_lm
     # Ensure out of box LC_RPATH on macOS with SIP
     INSTALL_RPATH_USE_LINK_PATH ON)
-target_compile_features(greedy_causal_lm PRIVATE cxx_std_11)
+target_compile_features(multinomial_causal_lm PRIVATE cxx_std_11)
 install(TARGETS multinomial_causal_lm
     RUNTIME DESTINATION samples_bin/
     COMPONENT samples_bin

diff --git a/samples/cpp/multinomial_causal_lm/README.md b/samples/cpp/multinomial_causal_lm/README.md
@@ -1,4 +1,4 @@
-# Text generation C++ multinomial_causal_lm that supports most popular models like LLaMA 2
+# Text generation C++ multinomial_causal_lm that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. For example, change the device for inference to GPU. The sample fearures `ov::genai::LLMPipeline` and configures it to run random sampling algorithm. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 

diff --git a/samples/cpp/prompt_lookup_decoding_lm/README.md b/samples/cpp/prompt_lookup_decoding_lm/README.md
@@ -1,4 +1,4 @@
-# prompt_lookup_decoding_lm C++ sample that supports most popular models like LLaMA 2
+# prompt_lookup_decoding_lm C++ sample that supports most popular models like LLaMA 3
 
 [Prompt Lookup decoding](https://github.com/apoorvumang/prompt-lookup-decoding) is [assested-generation](https://huggingface.co/blog/assisted-generation#understanding-text-generation-latency) technique where the draft model is replaced with simple string matching the prompt to generate candidate token sequences. This method highly effective for input grounded generation (summarization, document QA, multi-turn chat, code editing), where there is high n-gram overlap between LLM input (prompt) and LLM output. This could be entity names, phrases, or code chunks that the LLM directly copies from the input while generating the output. Prompt lookup exploits this pattern to speed up autoregressive decoding in LLMs. This results in significant speedups with no effect on output quality.
 

diff --git a/samples/cpp/speculative_decoding_lm/README.md b/samples/cpp/speculative_decoding_lm/README.md
@@ -1,4 +1,4 @@
-# speculative_decoding_lm C++ sample that supports most popular models like LLaMA 2
+# speculative_decoding_lm C++ sample that supports most popular models like LLaMA 3
 
 Speculative decoding (or [assisted-generation](https://huggingface.co/blog/assisted-generation#understanding-text-generation-latency) in HF terminology) is a recent technique, that allows to speed up token generation when an additional smaller draft model is used alonside with the main model.
 

diff --git a/samples/python/beam_search_causal_lm/README.md b/samples/python/beam_search_causal_lm/README.md
@@ -1,4 +1,4 @@
-# Text generation Python sample that supports most popular models like LLaMA 2
+# Text generation Python sample that supports most popular models like LLaMA 3
 
 This example showcases inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The application doesn't have many configuration options to encourage the reader to explore and modify the source code. It's only possible to change the device for inference to a differnt one, GPU for example, from the command line interface. The sample fearures `openvino_genai.LLMPipeline` and configures it to use multiple beam grops. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) which provides an example of LLM-powered Chatbot in Python.