FEAT: support sparse vector for bge-m3 #4999

Workflow file for this run

.github/workflows/python.yaml at bd5dd66

	name: Python CI

	on:
	push:
	branches:
	- '*'
	pull_request:
	types: ['opened', 'reopened', 'synchronize']

	concurrency:
	group: ${{ github.workflow }}-${{ github.ref }}
	cancel-in-progress: true

	jobs:
	lint:
	runs-on: ${{ matrix.os }}
	strategy:
	fail-fast: false
	matrix:
	os: [ "ubuntu-latest" ]
	python-version: [ "3.10" ]
	steps:
	- name: Check out code
	uses: actions/checkout@v3
	with:
	fetch-depth: 0
	submodules: recursive
	- name: Set up Python environment
	uses: actions/setup-python@v4
	with:
	python-version: "3.10"
	- name: flake8 Lint
	uses: py-actions/flake8@v2
	with:
	path: "xinference"
	args: "--config setup.cfg"
	- name: black
	uses: psf/black@stable
	with:
	src: "xinference"
	options: "--check"
	version: "23.12.0"
	- uses: isort/isort-action@master
	with:
	sortPaths: "xinference"
	configuration: "--check-only --diff --sp setup.cfg"
	- name: mypy
	run: pip install mypy && mypy --install-types --non-interactive xinference
	- name: codespell
	run: pip install codespell && codespell --ignore-words-list thirdparty xinference
	- name: Set up Node.js
	uses: actions/setup-node@v1
	with:
	node-version: 16
	# ESLint and Prettier must be in `package.json`
	- name: Install Node.js dependencies
	run: cd xinference/web/ui && npm ci
	- name: ESLint Check
	run: cd xinference/web/ui && npx eslint .
	- name: Prettier Check
	run: cd xinference/web/ui && ./node_modules/.bin/prettier --check .

	build_test_job:
	runs-on: ${{ matrix.os }}
	needs: lint
	env:
	CONDA_ENV: test
	SELF_HOST_PYTHON: /root/miniconda3/envs/inference_test/bin/python
	SELF_HOST_CONDA: /root/miniconda3/condabin/conda
	defaults:
	run:
	shell: bash -l {0}
	strategy:
	fail-fast: false
	matrix:
	os: [ "ubuntu-latest", "macos-12", "windows-latest" ]
	python-version: [ "3.9", "3.10", "3.11", "3.12" ]
	module: [ "xinference" ]
	exclude:
	- { os: macos-12, python-version: 3.10 }
	- { os: macos-12, python-version: 3.11 }
	- { os: windows-latest, python-version: 3.10 }
	- { os: windows-latest, python-version: 3.11 }
	include:
	- { os: self-hosted, module: gpu, python-version: 3.9}
	- { os: macos-latest, module: metal, python-version: "3.10" }

	steps:
	- name: Check out code
	uses: actions/checkout@v3
	with:
	fetch-depth: 0
	submodules: recursive

	- name: Set up conda ${{ matrix.python-version }}
	uses: conda-incubator/setup-miniconda@v3
	if: ${{ matrix.module != 'gpu' }}
	with:
	python-version: ${{ matrix.python-version }}
	activate-environment: ${{ env.CONDA_ENV }}

	# Important for python == 3.12
	- name: Update pip and setuptools
	if: ${{ matrix.python-version == '3.12' }}
	run: \|
	python -m pip install -U pip setuptools

	- name: Install dependencies
	env:
	MODULE: ${{ matrix.module }}
	OS: ${{ matrix.os }}
	if: ${{ matrix.module != 'gpu' }}
	run: \|
	if [ "$OS" == "ubuntu-latest" ]; then
	sudo rm -rf /usr/share/dotnet
	sudo rm -rf /opt/ghc
	sudo rm -rf "/usr/local/share/boost"
	sudo rm -rf "$AGENT_TOOLSDIRECTORY"
	fi
	if [ "$MODULE" == "metal" ]; then
	pip install mlx-lm
	fi
	pip install "llama-cpp-python==0.2.77" --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
	pip install transformers
	pip install attrdict
	pip install "timm>=0.9.16"
	pip install torch torchvision
	pip install accelerate
	pip install sentencepiece
	pip install transformers_stream_generator
	pip install bitsandbytes
	pip install "sentence-transformers>=2.3.1"
	pip install modelscope
	pip install diffusers
	pip install protobuf
	pip install FlagEmbedding
	pip install "tenacity>=8.2.0,<8.4.0"
	pip install -e ".[dev]"
	pip install "jinja2==3.1.2"
	pip install tensorizer
	pip install jj-pytorchvideo
	pip install qwen-vl-utils
	pip install datamodel_code_generator
	pip install jsonschema
	working-directory: .

	- name: Test with pytest
	env:
	MODULE: ${{ matrix.module }}
	run: \|
	if [ "$MODULE" == "gpu" ]; then
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "openai>1"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U modelscope
	${{ env.SELF_HOST_PYTHON }} -m pip install -U sse_starlette
	${{ env.SELF_HOST_PYTHON }} -m pip install -U xoscar
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "python-jose[cryptography]"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "passlib[bcrypt]"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "aioprometheus[starlette]"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "pynvml"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "transformers"
	${{ env.SELF_HOST_CONDA }} install -c conda-forge pynini=2.1.5
	${{ env.SELF_HOST_CONDA }} install -c conda-forge "ffmpeg<7"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U funasr
	${{ env.SELF_HOST_PYTHON }} -m pip install -U nemo_text_processing<1.1.0
	${{ env.SELF_HOST_PYTHON }} -m pip install -U omegaconf~=2.3.0
	${{ env.SELF_HOST_PYTHON }} -m pip install -U WeTextProcessing<1.0.4
	${{ env.SELF_HOST_PYTHON }} -m pip install -U librosa
	${{ env.SELF_HOST_PYTHON }} -m pip install -U xxhash
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "ChatTTS>=0.2.1"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U HyperPyYAML
	${{ env.SELF_HOST_PYTHON }} -m pip uninstall -y matcha-tts
	${{ env.SELF_HOST_PYTHON }} -m pip install -U onnxruntime-gpu==1.16.0; sys_platform == 'linux'
	${{ env.SELF_HOST_PYTHON }} -m pip install -U openai-whisper
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "torch==2.3.1" "torchaudio==2.3.1"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "loguru"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "natsort"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "loralib"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U "ormsgpack"
	${{ env.SELF_HOST_PYTHON }} -m pip uninstall -y opencc
	${{ env.SELF_HOST_PYTHON }} -m pip uninstall -y "faster_whisper"
	${{ env.SELF_HOST_PYTHON }} -m pip install -U accelerate
	${{ env.SELF_HOST_PYTHON }} -m pip install -U verovio
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	--disable-warnings \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/core/tests/test_continuous_batching.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/image/tests/test_stable_diffusion.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/image/tests/test_got_ocr2.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/audio/tests/test_whisper.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/audio/tests/test_funasr.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/audio/tests/test_chattts.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/audio/tests/test_cosyvoice.py && \
	${{ env.SELF_HOST_PYTHON }} -m pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/audio/tests/test_fish_speech.py
	elif [ "$MODULE" == "metal" ]; then
	pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/model/llm/mlx/tests/test_mlx.py
	else
	pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference xinference/client/tests/test_client.py
	pytest --timeout=1500 \
	-W ignore::PendingDeprecationWarning \
	--cov-config=setup.cfg --cov-report=xml --cov=xinference --ignore xinference/core/tests/test_continuous_batching.py --ignore xinference/client/tests/test_client.py --ignore xinference/model/image/tests/test_stable_diffusion.py --ignore xinference/model/image/tests/test_got_ocr2.py --ignore xinference/model/audio/tests xinference
	fi
	working-directory: .

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

FEAT: support sparse vector for bge-m3 #4999

Workflow file

FEAT: support sparse vector for bge-m3 #4999

Jobs

Run details

Workflow file for this run