[ci/build] Pin CI dependencies version with pip-compile (#9810)

Signed-off-by: kevin <kevin@anyscale.com>

Dockerfile.rocm

@@ -121,6 +121,8 @@ ARG GIT_REPO_CHECK=0
 RUN --mount=type=bind,source=.git,target=.git \
     if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
 
+RUN python3 -m pip install --upgrade pip
+
 # Package upgrades for useful functionality or to avoid dependency issues
 RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install --upgrade numba scipy huggingface-hub[cli] pytest-shard

requirements-test.in

+# testing
+pytest
+tensorizer>=2.9.0
+pytest-forked
+pytest-asyncio
+pytest-rerunfailures
+pytest-shard
+
+# testing utils
+awscli
+einops # required for MPT, qwen-vl and Mamba
+httpx
+librosa # required for audio tests
+opencv-python # required for video tests
+peft
+requests
+ray[adag]==2.35
+sentence-transformers # required for embedding
+soundfile # required for audio test
+timm # required for internvl test
+torch==2.5.0
+transformers_stream_generator # required for qwen-vl test
+matplotlib # required for qwen-vl test
+datamodel_code_generator # required for minicpm3 test
+lm-eval[api]==0.4.4 # required for model evaluation test
+
+# TODO: Add this after fully implementing llava(mantis)
+# git+https://github.com/TIGER-AI-Lab/Mantis.git # required for llava(mantis) test
+
+# Benchmarking
+aiohttp
+
+# quantization
+bitsandbytes>=0.44.0
+buildkite-test-collector==0.1.8
+
+numpy < 2.0.0

requirements-test.txt

-# testing
-pytest
-tensorizer>=2.9.0
-pytest-forked
-pytest-asyncio
-pytest-rerunfailures
-pytest-shard
-
-# testing utils
-awscli
-einops # required for MPT, qwen-vl and Mamba
-httpx
-librosa # required for audio tests
-opencv-python # required for video tests
-peft
-requests
-ray[adag]==2.35
-sentence-transformers # required for embedding
-soundfile # required for audio test
-timm # required for internvl test
-transformers_stream_generator # required for qwen-vl test
-matplotlib # required for qwen-vl test
-datamodel_code_generator # required for minicpm3 test
-lm-eval[api]==0.4.4 # required for model evaluation test
-
-# TODO: Add this after fully implementing llava(mantis)
-# git+https://github.com/TIGER-AI-Lab/Mantis.git # required for llava(mantis) test
-
-# Benchmarking
-aiohttp
-
-# quantization
-bitsandbytes>=0.44.0
+#
+# This file is autogenerated by pip-compile with Python 3.12
+# by the following command:
+#
+#    pip-compile --output-file=requirements-test.txt requirements-test.in
+#
+absl-py==2.1.0
+    # via rouge-score
+accelerate==1.0.1
+    # via
+    #   lm-eval
+    #   peft
+aiohappyeyeballs==2.4.3
+    # via aiohttp
+aiohttp==3.10.10
+    # via
+    #   -r requirements-test.in
+    #   datasets
+    #   fsspec
+    #   lm-eval
+aiosignal==1.3.1
+    # via
+    #   aiohttp
+    #   ray
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.6.2.post1
+    # via httpx
+argcomplete==3.5.1
+    # via datamodel-code-generator
+attrs==24.2.0
+    # via
+    #   aiohttp
+    #   jsonlines
+    #   jsonschema
+    #   referencing
+audioread==3.0.1
+    # via librosa
+awscli==1.35.16
+    # via -r requirements-test.in
+bitsandbytes==0.44.1
+    # via -r requirements-test.in
+black==24.10.0
+    # via datamodel-code-generator
+boto3==1.35.50
+    # via tensorizer
+botocore==1.35.50
+    # via
+    #   awscli
+    #   boto3
+    #   s3transfer
 buildkite-test-collector==0.1.8
+    # via -r requirements-test.in
+certifi==2024.8.30
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+cffi==1.17.1
+    # via soundfile
+chardet==5.2.0
+    # via mbstrdecoder
+charset-normalizer==3.4.0
+    # via requests
+click==8.1.7
+    # via
+    #   black
+    #   nltk
+    #   ray
+colorama==0.4.6
+    # via
+    #   awscli
+    #   sacrebleu
+    #   tqdm-multiprocess
+contourpy==1.3.0
+    # via matplotlib
+cupy-cuda12x==13.3.0
+    # via ray
+cycler==0.12.1
+    # via matplotlib
+datamodel-code-generator==0.26.2
+    # via -r requirements-test.in
+dataproperty==1.0.1
+    # via
+    #   pytablewriter
+    #   tabledata
+datasets==3.0.2
+    # via
+    #   evaluate
+    #   lm-eval
+decorator==5.1.1
+    # via librosa
+dill==0.3.8
+    # via
+    #   datasets
+    #   evaluate
+    #   lm-eval
+    #   multiprocess
+dnspython==2.7.0
+    # via email-validator
+docutils==0.16
+    # via awscli
+einops==0.8.0
+    # via -r requirements-test.in
+email-validator==2.2.0
+    # via pydantic
+evaluate==0.4.3
+    # via lm-eval
+fastrlock==0.8.2
+    # via cupy-cuda12x
+filelock==3.16.1
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   ray
+    #   torch
+    #   transformers
+    #   triton
+fonttools==4.54.1
+    # via matplotlib
+frozenlist==1.5.0
+    # via
+    #   aiohttp
+    #   aiosignal
+    #   ray
+fsspec[http]==2024.9.0
+    # via
+    #   datasets
+    #   evaluate
+    #   huggingface-hub
+    #   torch
+genson==1.3.0
+    # via datamodel-code-generator
+h11==0.14.0
+    # via httpcore
+hiredis==3.0.0
+    # via tensorizer
+httpcore==1.0.6
+    # via httpx
+httpx==0.27.2
+    # via -r requirements-test.in
+huggingface-hub==0.26.2
+    # via
+    #   accelerate
+    #   datasets
+    #   evaluate
+    #   peft
+    #   sentence-transformers
+    #   timm
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   email-validator
+    #   httpx
+    #   requests
+    #   yarl
+inflect==5.6.2
+    # via datamodel-code-generator
+iniconfig==2.0.0
+    # via pytest
+isort==5.13.2
+    # via datamodel-code-generator
+jinja2==3.1.4
+    # via
+    #   datamodel-code-generator
+    #   torch
+jmespath==1.0.1
+    # via
+    #   boto3
+    #   botocore
+joblib==1.4.2
+    # via
+    #   librosa
+    #   nltk
+    #   scikit-learn
+jsonlines==4.0.0
+    # via lm-eval
+jsonschema==4.23.0
+    # via ray
+jsonschema-specifications==2024.10.1
+    # via jsonschema
+kiwisolver==1.4.7
+    # via matplotlib
+lazy-loader==0.4
+    # via librosa
+libnacl==2.1.0
+    # via tensorizer
+librosa==0.10.2.post1
+    # via -r requirements-test.in
+llvmlite==0.43.0
+    # via numba
+lm-eval[api]==0.4.4
+    # via -r requirements-test.in
+lxml==5.3.0
+    # via sacrebleu
+markupsafe==3.0.2
+    # via jinja2
+matplotlib==3.9.2
+    # via -r requirements-test.in
+mbstrdecoder==1.1.3
+    # via
+    #   dataproperty
+    #   pytablewriter
+    #   typepy
+more-itertools==10.5.0
+    # via lm-eval
+mpmath==1.3.0
+    # via sympy
+msgpack==1.1.0
+    # via
+    #   librosa
+    #   ray
+multidict==6.1.0
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.16
+    # via
+    #   datasets
+    #   evaluate
+mypy-extensions==1.0.0
+    # via black
+networkx==3.2.1
+    # via torch
+nltk==3.9.1
+    # via rouge-score
+numba==0.60.0
+    # via librosa
+numexpr==2.10.1
+    # via lm-eval
+numpy==1.26.4
+    # via
+    #   -r requirements-test.in
+    #   accelerate
+    #   bitsandbytes
+    #   contourpy
+    #   cupy-cuda12x
+    #   datasets
+    #   evaluate
+    #   librosa
+    #   matplotlib
+    #   numba
+    #   numexpr
+    #   opencv-python
+    #   pandas
+    #   peft
+    #   rouge-score
+    #   sacrebleu
+    #   scikit-learn
+    #   scipy
+    #   soxr
+    #   tensorizer
+    #   torchvision
+    #   transformers
+nvidia-cublas-cu12==12.4.5.8
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.4.127
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.4.127
+    # via torch
+nvidia-cuda-runtime-cu12==12.4.127
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.2.1.3
+    # via torch
+nvidia-curand-cu12==10.3.5.147
+    # via torch
+nvidia-cusolver-cu12==11.6.1.9
+    # via torch
+nvidia-cusparse-cu12==12.3.1.170
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-nccl-cu12==2.21.5
+    # via torch
+nvidia-nvjitlink-cu12==12.4.127
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+    #   torch
+nvidia-nvtx-cu12==12.4.127
+    # via torch
+opencv-python==4.10.0.84
+    # via -r requirements-test.in
+packaging==24.1
+    # via
+    #   accelerate
+    #   black
+    #   datamodel-code-generator
+    #   datasets
+    #   evaluate
+    #   huggingface-hub
+    #   lazy-loader
+    #   matplotlib
+    #   peft
+    #   pooch
+    #   pytest
+    #   pytest-rerunfailures
+    #   ray
+    #   transformers
+    #   typepy
+pandas==2.2.3
+    # via
+    #   datasets
+    #   evaluate
+pathspec==0.12.1
+    # via black
+pathvalidate==3.2.1
+    # via pytablewriter
+peft==0.13.2
+    # via
+    #   -r requirements-test.in
+    #   lm-eval
+pillow==11.0.0
+    # via
+    #   matplotlib
+    #   sentence-transformers
+    #   torchvision
+platformdirs==4.3.6
+    # via
+    #   black
+    #   pooch
+pluggy==1.5.0
+    # via pytest
+pooch==1.8.2
+    # via librosa
+portalocker==2.10.1
+    # via sacrebleu
+propcache==0.2.0
+    # via yarl
+protobuf==5.28.3
+    # via
+    #   ray
+    #   tensorizer
+psutil==6.1.0
+    # via
+    #   accelerate
+    #   peft
+    #   tensorizer
+py==1.11.0
+    # via pytest-forked
+pyarrow==18.0.0
+    # via datasets
+pyasn1==0.6.1
+    # via rsa
+pybind11==2.13.6
+    # via lm-eval
+pycparser==2.22
+    # via cffi
+pydantic[email]==2.9.2
+    # via datamodel-code-generator
+pydantic-core==2.23.4
+    # via pydantic
+pyparsing==3.2.0
+    # via matplotlib
+pytablewriter==1.2.0
+    # via lm-eval
+pytest==8.3.3
+    # via
+    #   -r requirements-test.in
+    #   buildkite-test-collector
+    #   pytest-asyncio
+    #   pytest-forked
+    #   pytest-rerunfailures
+    #   pytest-shard
+pytest-asyncio==0.24.0
+    # via -r requirements-test.in
+pytest-forked==1.6.0
+    # via -r requirements-test.in
+pytest-rerunfailures==14.0
+    # via -r requirements-test.in
+pytest-shard==0.1.2
+    # via -r requirements-test.in
+python-dateutil==2.9.0.post0
+    # via
+    #   botocore
+    #   matplotlib
+    #   pandas
+    #   typepy
+pytz==2024.2
+    # via
+    #   pandas
+    #   typepy
+pyyaml==6.0.2
+    # via
+    #   accelerate
+    #   awscli
+    #   datamodel-code-generator
+    #   datasets
+    #   huggingface-hub
+    #   peft
+    #   ray
+    #   timm
+    #   transformers
+ray[adag]==2.35.0
+    # via -r requirements-test.in
+redis==5.2.0
+    # via tensorizer
+referencing==0.35.1
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+regex==2024.9.11
+    # via
+    #   nltk
+    #   sacrebleu
+    #   tiktoken
+    #   transformers
+requests==2.32.3
+    # via
+    #   -r requirements-test.in
+    #   buildkite-test-collector
+    #   datasets
+    #   evaluate
+    #   huggingface-hub
+    #   lm-eval
+    #   pooch
+    #   ray
+    #   tiktoken
+    #   transformers
+rouge-score==0.1.2
+    # via lm-eval
+rpds-py==0.20.0
+    # via
+    #   jsonschema
+    #   referencing
+rsa==4.7.2
+    # via awscli
+s3transfer==0.10.3
+    # via
+    #   awscli
+    #   boto3
+sacrebleu==2.4.3
+    # via lm-eval
+safetensors==0.4.5
+    # via
+    #   accelerate
+    #   peft
+    #   timm
+    #   transformers
+scikit-learn==1.5.2
+    # via
+    #   librosa
+    #   lm-eval
+    #   sentence-transformers
+scipy==1.13.1
+    # via
+    #   librosa
+    #   scikit-learn
+    #   sentence-transformers
+sentence-transformers==3.2.1
+    # via -r requirements-test.in
+six==1.16.0
+    # via
+    #   python-dateutil
+    #   rouge-score
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
+soundfile==0.12.1
+    # via
+    #   -r requirements-test.in
+    #   librosa
+soxr==0.5.0.post1
+    # via librosa
+sqlitedict==2.1.0
+    # via lm-eval
+sympy==1.13.1
+    # via torch
+tabledata==1.3.3
+    # via pytablewriter
+tabulate==0.9.0
+    # via sacrebleu
+tcolorpy==0.1.6
+    # via pytablewriter
+tenacity==9.0.0
+    # via lm-eval
+tensorizer==2.9.0
+    # via -r requirements-test.in
+threadpoolctl==3.5.0
+    # via scikit-learn
+tiktoken==0.8.0
+    # via lm-eval
+timm==1.0.11
+    # via -r requirements-test.in
+tokenizers==0.20.1
+    # via transformers
+torch==2.5.0
+    # via
+    #   -r requirements-test.in
+    #   accelerate
+    #   bitsandbytes
+    #   lm-eval
+    #   peft
+    #   sentence-transformers
+    #   tensorizer
+    #   timm
+    #   torchvision
+torchvision==0.20.0
+    # via timm
+tqdm==4.66.6
+    # via
+    #   datasets
+    #   evaluate
+    #   huggingface-hub
+    #   lm-eval
+    #   nltk
+    #   peft
+    #   sentence-transformers
+    #   tqdm-multiprocess
+    #   transformers
+tqdm-multiprocess==0.0.11
+    # via lm-eval
+transformers==4.45.2
+    # via
+    #   lm-eval
+    #   peft
+    #   sentence-transformers
+    #   transformers-stream-generator
+transformers-stream-generator==0.0.5
+    # via -r requirements-test.in
+triton==3.1.0
+    # via torch
+typepy[datetime]==1.3.2
+    # via
+    #   dataproperty
+    #   pytablewriter
+    #   tabledata
+typing-extensions==4.12.2
+    # via
+    #   huggingface-hub
+    #   librosa
+    #   pydantic
+    #   pydantic-core
+    #   torch
+tzdata==2024.2
+    # via pandas
+urllib3==1.26.20
+    # via
+    #   botocore
+    #   requests
+word2number==1.1
+    # via lm-eval
+xxhash==3.5.0
+    # via
+    #   datasets
+    #   evaluate
+yarl==1.17.0
+    # via aiohttp
+zstandard==0.23.0
+    # via lm-eval
+
+# The following packages are considered to be unsafe in a requirements file:
+# setuptools