Merge branch 'master' into late_init

.github/dependabot.yml

@@ -17,6 +17,6 @@ updates:
     schedule:
       interval: "weekly"
   - package-ecosystem: "pip"
-    directory: "text_generation/causal_lm/cpp/"
+    directory: "samples/"
     schedule:
       interval: "weekly"

.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/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
+  l_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.4.0-16161-d253f4fd89c/l_openvino_toolkit_ubuntu20_2024.4.0.dev20240730_x86_64.tgz
+  m_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.4.0-16161-d253f4fd89c/m_openvino_toolkit_macos_12_6_2024.4.0.dev20240730_x86_64.tgz
+  w_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.4.0-16161-d253f4fd89c/w_openvino_toolkit_windows_2024.4.0.dev20240730_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] --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 && 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 && 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] --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 && 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 && 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] --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 && 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 && 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"
@@ -113,5 +113,6 @@ jobs:
           && cmake --install "samples build" --config ${{ matrix.build-type }} --component samples_bin --prefix samples_install
         if: ${{ 'Release' != matrix.build-type }}
       - run: call ov\setupvars.bat && "${{ github.workspace }}/samples_install/samples_bin/greedy_causal_lm" .\TinyLlama-1.1B-Chat-v1.0\ ""
+        if: ${{ 'Release' == matrix.build-type }} # Tokenizers don't work in debug
       - run: call ov\setupvars.bat && python .\ov\samples\python\multinomial_causal_lm\multinomial_causal_lm.py .\TinyLlama-1.1B-Chat-v1.0\ 0
         if: ${{ 'Release' == matrix.build-type }} # Python bindings can be built in Release only

.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/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
+  l_ov_centos_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.4.0-16161-d253f4fd89c/l_openvino_toolkit_centos7_2024.4.0.dev20240730_x86_64.tgz
+  m_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.4.0-16161-d253f4fd89c/m_openvino_toolkit_macos_12_6_2024.4.0.dev20240730_x86_64.tgz
+  w_ov_link: https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.4.0-16161-d253f4fd89c/w_openvino_toolkit_windows_2024.4.0.dev20240730_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 --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --upgrade-strategy eager
+      - 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 && PYTHONPATH=./build/:$PYTHONPATH python -m pytest ./tests/python_tests/
       - run: source ./ov/setupvars.sh && python -m pip install . --verbose
       - run: python -m pytest ./tests/python_tests/
@@ -52,7 +52,7 @@ jobs:
       - run: brew install coreutils scons
       - run: source ./ov/setupvars.sh && cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
       - run: source ./ov/setupvars.sh && cmake --build ./build/ --config Release -j
-      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release --upgrade-strategy eager
+      - run: source ./ov/setupvars.sh && python -m pip install ./thirdparty/openvino_tokenizers/[transformers] -r ./tests/python_tests/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly --upgrade-strategy eager
       - run: source ./ov/setupvars.sh && PYTHONPATH=./build/:$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"
@@ -81,7 +81,7 @@ jobs:
         shell: bash
       - 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
+      - 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
       # 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

.github/workflows/lcm_dreamshaper_cpp.yml

@@ -43,15 +43,15 @@ jobs:
         run: |
           conda activate openvino_lcm_cpp
           conda update -c conda-forge --all
-          conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.3.0.dev20240614 c-compiler cxx-compiler git make cmake
+          conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.4.0.dev20240726 c-compiler cxx-compiler git make cmake
           conda env config vars set LD_LIBRARY_PATH=$CONDA_PREFIX/lib:$LD_LIBRARY_PATH
       
       - name: Install python dependencies
         working-directory: ${{ env.working_directory }}
         run: |
           conda activate openvino_lcm_cpp
-          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
+          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
           
       - name: Download and convert model and tokenizer
         working-directory: ${{ env.working_directory }}
@@ -88,15 +88,15 @@ jobs:
         run: |
           conda activate openvino_lcm_cpp
           conda update -c conda-forge --all
-          conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.3.0.dev20240614 c-compiler cxx-compiler git make cmake
+          conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.4.0.dev20240726 c-compiler cxx-compiler git make cmake
           conda env config vars set LD_LIBRARY_PATH=$CONDA_PREFIX/lib:$LD_LIBRARY_PATH
       
       - name: Install python dependencies
         working-directory: ${{ env.working_directory }}
         run: |
           conda activate openvino_lcm_cpp
-          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
+          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
 
       - name: Download and convert model and tokenizer
         working-directory: ${{ env.working_directory }}

.github/workflows/stable_diffusion_1_5_cpp.yml

@@ -42,15 +42,15 @@ jobs:
       - name: Install OpenVINO and other conda dependencies
         run: |
           conda activate openvino_sd_cpp
-          conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.3.0.dev20240614 c-compiler cxx-compiler git make cmake
+          conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.4.0.dev20240726 c-compiler cxx-compiler git make cmake
           conda env config vars set LD_LIBRARY_PATH=$CONDA_PREFIX/lib:$LD_LIBRARY_PATH
 
       - name: Install python dependencies
         working-directory: ${{ env.working_directory }}
         run: |
           conda activate openvino_sd_cpp
-          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
+          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
 
       - name: Download and convert model and tokenizer
         working-directory: ${{ env.working_directory }}
@@ -86,7 +86,7 @@ jobs:
         - name: Install OpenVINO and other conda dependencies
           run: |
             conda activate openvino_sd_cpp
-            conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.3.0.dev20240614 c-compiler cxx-compiler git make cmake
+            conda install -c conda-forge -c conda-forge/label/openvino_dev openvino==2024.4.0.dev20240726 c-compiler cxx-compiler git make cmake
   
         - name: Install python dependencies
           working-directory: ${{ env.working_directory }}

llm_bench/python/requirements.txt

@@ -10,7 +10,7 @@ torch
 transformers>=4.40.0
 diffusers>=0.22.0
 #optimum is in dependency list of optimum-intel 
-git+https://github.com/huggingface/optimum-intel.git@439d61f79cf55d5d0b28334f577b6ac3c5ced28f#egg=optimum-intel
+git+https://github.com/huggingface/optimum-intel.git@6388aeb8738b63e28fc594af84df94590e77cb9a#egg=optimum-intel
 git+https://github.com/openvinotoolkit/nncf.git@develop#egg=nncf
 packaging
 psutil

llm_bench/python/utils/conversion_utils/helpers.py

@@ -189,7 +189,11 @@ def compress_ov_model_weights_helper(ov_model, tok, config, out_path, compress_w
     if "INT8" in compress_weights_format and "INT8_ASYM" in COMPRESSION_OPTIONS:
         warnings.warn("Usage INT8 mode is deprecated and will be removed soon. Please use INT8_ASYM instead", DeprecationWarning)
     if "4BIT_DEFAULT" in compress_weights_format:
-        compression_args = _check_default_4bit_configs(config)
+        try:
+            # TODO: remove this path when support of an older version optimum-intel is deprecated
+            compression_args = _check_default_4bit_configs(config)
+        except TypeError:
+            compression_args = _check_default_4bit_configs(config.name_or_path)
         if compression_args:
             sym = compression_args.pop("sym", False)
             compression_args.pop("bits", 4)

pyproject.toml

@@ -16,7 +16,7 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
 ]
 dependencies = [
-    "openvino_tokenizers~=2024.3.0.0.dev"
+    "openvino_tokenizers~=2024.4.0.0.dev"
 ]
 
 [tool.py-build-cmake.module]

samples/cpp/chat_sample/README.md

@@ -34,3 +34,11 @@ UnicodeEncodeError: 'charmap' codec can't encode character '\u25aa' in position
 If you encounter the error described in the example when sample is printing output to the Windows console, it is likely due to the default Windows encoding not supporting certain Unicode characters. To resolve this:
 1. Enable Unicode characters for Windows cmd - open `Region` settings from `Control panel`. `Administrative`->`Change system locale`->`Beta: Use Unicode UTF-8 for worldwide language support`->`OK`. Reboot.
 2. Enable UTF-8 mode by setting environment variable `PYTHONIOENCODING="utf8"`.
+
+#### Missing chat template
+
+If you encounter an exception indicating a missing "chat template" when launching the `ov::genai::LLMPipeline` in chat mode, it likely means the model was not tuned for chat functionality. To work this around, manually add the chat template to tokenizer_config.json of your model.
+The following template can be used as a default, but it may not work properly with every model:
+```
+"chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n<|im_start|>assistant\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>\n'}}{% endif %}{% endfor %}",
+```

samples/python/chat_sample/README.md

@@ -22,3 +22,13 @@ To enable Unicode characters for Windows cmd open `Region` settings from `Contro
 Discrete GPUs (dGPUs) usually provide better performance compared to CPUs. It is recommended to run larger models on a dGPU with 32GB+ RAM. For example, the model meta-llama/Llama-2-13b-chat-hf can benefit from being run on a dGPU. Modify the source code to change the device for inference to the GPU.
 
 See https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md#supported-models for the list of supported models.
+
+
+## Troubleshooting
+### Missing chat template
+
+If you encounter an exception indicating a missing "chat template" when launching the `ov::genai::LLMPipeline` in chat mode, it likely means the model was not tuned for chat functionality. To work this around, manually add the chat template to tokenizer_config.json of your model.
+The following template can be used as a default, but it may not work properly with every model:
+```
+"chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n<|im_start|>assistant\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>\n'}}{% endif %}{% endfor %}",
+```

samples/requirements.txt

@@ -1,4 +1,4 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
-optimum[openvino]==1.20.0
+optimum[openvino]==1.21.2
 einops==0.8.0  # For Qwen
 transformers_stream_generator==0.0.5  # For Qwen

src/cpp/src/block_manager.hpp

@@ -277,7 +277,6 @@ class BlockManager {
             }
             phisical_blocks_released += released_count;
         }
-        phisical_blocks_released = phisical_blocks_released;
         return num_required_blocks <= phisical_blocks_released;
     }