From b30a2626028d0bb751a6f3639bab0a3440c8ad03 Mon Sep 17 00:00:00 2001 From: Wovchena Date: Fri, 2 Aug 2024 17:35:57 +0400 Subject: [PATCH] fix merge --- .github/workflows/causal_lm_cpp.yml | 60 +++++++++---------- .github/workflows/genai_package.yml | 12 ++-- .github/workflows/genai_python_lib.yml | 6 +- .github/workflows/lcm_dreamshaper_cpp.yml | 8 +-- .../workflows/stable_diffusion_1_5_cpp.yml | 4 +- llm_bench/python/requirements.txt | 11 ++-- llm_bench/python/utils/nncf_utils.py | 4 +- .../include/openvino/genai/llm_pipeline.hpp | 2 +- src/docs/BUILD.md | 35 ----------- src/python/py_generate_pipeline.cpp | 1 + tests/python_tests/test_generate_api.py | 3 - 11 files changed, 54 insertions(+), 92 deletions(-) diff --git a/.github/workflows/causal_lm_cpp.yml b/.github/workflows/causal_lm_cpp.yml index 99b98a9064..2263277b68 100644 --- a/.github/workflows/causal_lm_cpp.yml +++ b/.github/workflows/causal_lm_cpp.yml @@ -34,8 +34,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -77,8 +77,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -210,8 +210,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -255,8 +255,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -282,8 +282,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -310,8 +310,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -338,8 +338,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -366,8 +366,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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/ @@ -403,8 +403,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -447,8 +447,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -495,8 +495,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -545,8 +545,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -605,8 +605,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -650,8 +650,8 @@ jobs: - name: Install dependencies and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 @@ -691,8 +691,8 @@ jobs: - name: Download, convert and build 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 - python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release + python -m pip install --upgrade-strategy eager -r ./samples/requirements.txt --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly + python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly 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 diff --git a/.github/workflows/genai_package.yml b/.github/workflows/genai_package.yml index c401926b08..d89ad2097b 100644 --- a/.github/workflows/genai_package.yml +++ b/.github/workflows/genai_package.yml @@ -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" diff --git a/.github/workflows/genai_python_lib.yml b/.github/workflows/genai_python_lib.yml index 825c9500c6..58e340a5b9 100644 --- a/.github/workflows/genai_python_lib.yml +++ b/.github/workflows/genai_python_lib.yml @@ -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 diff --git a/.github/workflows/lcm_dreamshaper_cpp.yml b/.github/workflows/lcm_dreamshaper_cpp.yml index b59e7014d2..8d6398027b 100644 --- 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] --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 }} @@ -95,8 +95,8 @@ jobs: 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 }} diff --git a/.github/workflows/stable_diffusion_1_5_cpp.yml b/.github/workflows/stable_diffusion_1_5_cpp.yml index 4f323dc218..c947bdb4b0 100644 --- 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] --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 }} diff --git a/llm_bench/python/requirements.txt b/llm_bench/python/requirements.txt index 40d17b2346..bbeb5de89e 100644 --- a/llm_bench/python/requirements.txt +++ b/llm_bench/python/requirements.txt @@ -1,14 +1,13 @@ --extra-index-url https://download.pytorch.org/whl/cpu numpy --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly -openvino~=2024.3.0 -openvino-tokenizers~=2024.3.0 -openvino_genai~=2024.3.0 +openvino +openvino-tokenizers +openvino_genai auto-gptq>=0.5.1 # for gptq pillow -torch<2.5.0 -torchvision<0.20.0 -transformers>=4.40.0,<4.43.0 +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@6388aeb8738b63e28fc594af84df94590e77cb9a#egg=optimum-intel diff --git a/llm_bench/python/utils/nncf_utils.py b/llm_bench/python/utils/nncf_utils.py index d89f21aaf2..01d0dd95b3 100644 --- a/llm_bench/python/utils/nncf_utils.py +++ b/llm_bench/python/utils/nncf_utils.py @@ -38,7 +38,7 @@ def get_compressed_path(output_dir: str, base_precision, option: str): INT4_MODEL_CONFIGURATION = { - "dolly-v2-3b": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 1.0, "scale": True}, + "dolly-v2-3b": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 0.8}, "gpt-j-6b": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 64}, "opt-6.7b": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 64, "ratio": 0.8}, "red-pajama-incite-7b-instruct": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128}, @@ -69,7 +69,7 @@ def get_compressed_path(output_dir: str, base_precision, option: str): "mistral-7b-v0.1": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 128, "ratio": 0.9}, "llama-7b": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 128, "ratio": 0.7}, "opt-2.7b": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 128, "ratio": 0.7}, - "red-pajama-incite-chat-3b-v1": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 1.0, "scale": True}, + "red-pajama-incite-chat-3b-v1": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 0.8}, "vicuna-7b-v1.5": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 1.0}, "stablelm-tuned-alpha-3b": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 0.8}, "longchat-b7": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 128, "ratio": 0.9}, diff --git a/src/cpp/include/openvino/genai/llm_pipeline.hpp b/src/cpp/include/openvino/genai/llm_pipeline.hpp index e79a6e65f0..4be298128e 100644 --- a/src/cpp/include/openvino/genai/llm_pipeline.hpp +++ b/src/cpp/include/openvino/genai/llm_pipeline.hpp @@ -16,7 +16,7 @@ namespace ov { namespace genai { -// Return flag correspods whether generation should be stopped: false means continue generation, true means stop. +// Return flag corresponds whether generation should be stopped: false means continue generation, true means stop. using StreamerVariant = std::variant, std::shared_ptr, std::monostate>; using OptionalGenerationConfig = std::optional; using EncodedInputs = std::variant; diff --git a/src/docs/BUILD.md b/src/docs/BUILD.md index 5a3b4d2eb4..548309b7d7 100644 --- a/src/docs/BUILD.md +++ b/src/docs/BUILD.md @@ -146,7 +146,6 @@ For more information please refer to the [OpenVINO Tokenizers instructions](http ### Build OpenVINO GenAI Wheel -<<<<<<< HEAD 1. Build and install OpenVINO from sources following the [instructions](https://github.com/openvinotoolkit/openvino/wiki#how-to-build) The path to the openvino install directory is referred as throughout the document. @@ -176,8 +175,6 @@ The path to the openvino install directory is referred as througho ``` ### Install OpenVINO GenAI From Source -======= ->>>>>>> releases/2024/3 1. Clone OpenVINO GenAI repository and init submodules: ```sh @@ -199,40 +196,8 @@ The path to the openvino install directory is referred as througho ```sh python -m pip install --upgrade pip ``` -<<<<<<< HEAD 4. Install the package directly from source: ```sh -======= -4. Build the wheel in the `dist` directory: - ```sh - python -m pip wheel . -w dist/ --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release - ``` - -### Install OpenVINO GenAI From Source - -1. Clone OpenVINO GenAI repository and init submodules: - ```sh - git clone --recursive https://github.com/openvinotoolkit/openvino.genai.git - cd openvino.genai - ``` -2. Set up the environment: - - Option 1 - using OpenVINO `setupvars.sh` script: - ```sh - source /setupvars.sh - ``` - - Option 2 - setting environment variables manually: - ```sh - export OpenVINO_DIR=/runtime - export PYTHONPATH=/python:./build/:$PYTHONPATH - export LD_LIBRARY_PATH=/runtime/lib/intel64:$LD_LIBRARY_PATH - ``` -3. Upgrade pip to ensure you have the latest version: - ```sh - python -m pip install --upgrade pip - ``` -4. Install the package directly from source: - ```sh ->>>>>>> releases/2024/3 python -m pip install . ``` 5. To verify the installation, run a simple Python script: diff --git a/src/python/py_generate_pipeline.cpp b/src/python/py_generate_pipeline.cpp index 128f9c12d1..a429fc4801 100644 --- a/src/python/py_generate_pipeline.cpp +++ b/src/python/py_generate_pipeline.cpp @@ -751,6 +751,7 @@ PYBIND11_MODULE(py_generate_pipeline, m) { .def(py::init<>()) .def_readwrite("max_num_batched_tokens", &SchedulerConfig::max_num_batched_tokens) .def_readwrite("num_kv_blocks", &SchedulerConfig::num_kv_blocks) + .def_readwrite("cache_size", &SchedulerConfig::cache_size) .def_readwrite("block_size", &SchedulerConfig::block_size) .def_readwrite("dynamic_split_fuse", &SchedulerConfig::dynamic_split_fuse) .def_readwrite("max_num_seqs", &SchedulerConfig::max_num_seqs) diff --git a/tests/python_tests/test_generate_api.py b/tests/python_tests/test_generate_api.py index b62a7890d7..fe306e2a37 100644 --- a/tests/python_tests/test_generate_api.py +++ b/tests/python_tests/test_generate_api.py @@ -731,10 +731,7 @@ def test_continuous_batching_vs_stateful(model_descr, prompt, generation_config) @pytest.mark.parametrize("prompt", prompts) @pytest.mark.parametrize("model_descr", get_models_list()) @pytest.mark.precommit -<<<<<<< HEAD @pytest.mark.skip("continuous_batching seg faults with nightly ov. Ticket 147793") -======= ->>>>>>> releases/2024/3 def test_cb_streamer_vs_return_vs_stateful(model_descr, prompt): model_id, path, tokenizer, model, stateful = read_model(( "TinyLlama/TinyLlama-1.1B-Chat-v1.0",