Skip to content

[Python] Upgrade the vLLM extra to 0.32.0 #41005

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
bvolpato wants to merge 1 commit into
base: master
Choose a base branch
from
+7 −183
Draft

[Python] Upgrade the vLLM extra to 0.32.0 #41005

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,7 @@

### Package upgrades
* [comment]: dependency upgrades (e.g. major version) and migrations that may introduce breaking change
* (Python) Upgraded the `vllm` extra to vLLM 0.32.0, which requires `openai>=2.25.0`, `transformers>=5.16.1`, and `torch==2.13.0`. The GPU image requirements no longer include vLLM. To install vLLM, use the `vllm` extra ([#41005](https://github.com/apache/beam/issues/41005)).

### API changes
* [comment]: Public facing interface changes that may introduce breaking change or change of behaviors
Expand Down
4 changes: 2 additions & 2 deletions sdks/python/apache_beam/ml/inference/vllm_tests_requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
torch>=1.7.1
torchvision>=0.8.2
pillow>=8.0.0
transformers==4.57.1
transformers>=5.16.1,<5.20.0
sentencepiece==0.2.1
google-cloud-monitoring>=2.27.0
openai>=1.52.2
openai>=2.25.0,<3.0.0
5 changes: 3 additions & 2 deletions sdks/python/container/common.gradle
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,15 +66,16 @@ def generatePythonRequirements = tasks.register("generatePythonRequirements") {
if ("${project.ext.pythonVersion}" != "3.13" && "${project.ext.pythonVersion}" != "3.14") {
// GPU requirements not used for any containers directly due to
// licensing, but can be picked up by customers or other consumers for
// use.
// use. This list excludes the vllm extra because vLLM pins a torch version
// above the cap in the transformers extra. Install vLLM with that extra.
exec {
executable 'sh'
args '-c', "cd ${rootDir} && ${runScriptsPath} " +
"${project.ext.pythonVersion} " +
"${files(configurations.sdkSourceTarball.files).singleFile} " +
"gpu_image_requirements.txt " +
"container/ml " +
"[gcp,dataframe,test,tensorflow,tfrecord,torch,transformers,vllm] " +
"[gcp,dataframe,test,tensorflow,tfrecord,torch,transformers] " +
"${pipExtraOptions}"
}
}
Expand Down
89 changes: 0 additions & 89 deletions sdks/python/container/ml/py311/gpu_image_requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@
# Reach out to a committer if you need help.

absl-py==2.5.1
agent-detector==2.0.0
aiohappyeyeballs==2.7.1
aiohttp==3.14.5
aiosignal==1.4.0
Expand All @@ -31,49 +30,32 @@ annotated-types==0.8.0
anyio==4.16.0
arro3-core==0.9.1
asn1crypto==1.5.1
astor==0.8.1
astunparse==1.6.3
attrs==26.1.0
backports.tarfile==1.2.0
beartype==0.22.9
beautifulsoup4==4.15.0
blake3==1.0.11
bs4==0.0.2
build==1.6.1
cachetools==6.2.6
cbor2==6.2.0.post2
certifi==2026.10.23
cffi==2.1.1
charset-normalizer==3.5.2
click==8.5.0
cloud-sql-python-connector==1.23.0
cloudpickle==3.1.2
compressed-tensors==0.10.2
crcmod==1.7
cryptography==50.0.2
cuda-bindings==13.4.4
cuda-pathfinder==1.8.5
cuda-toolkit==13.2.2
cupy-cuda12x==14.2.0
Cython==3.3.1
defusedxml==0.7.1
deltalake==1.6.6
Deprecated==1.3.1
depyf==0.19.0
detect-installer==0.2.1
dill==0.3.1.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.9.1
docker==7.2.0
docstring_parser==0.18.0
einops==0.8.2
email-validator==2.3.0
execnet==2.1.2
fastapi==0.162.0
fastapi-cli==0.0.32
fastapi-cloud-cli==0.26.0
fastar==0.12.0
fastavro==1.13.1
fasteners==0.20
filelock==4.2.7
Expand All @@ -83,7 +65,6 @@ frozenlist==1.8.0
fsspec==2026.9.0
future==1.0.0
gast==0.7.0
gguf==0.19.0
google-api-core==2.43.2
google-api-python-client==2.201.0
google-apitools==0.5.31
Expand Down Expand Up @@ -129,7 +110,6 @@ hpack==4.2.0
httpcore==1.0.9
httpcore2==2.16.0
httplib2==0.32.1
httptools==0.9.0
httpx==0.28.1
httpx2==2.16.0
huggingface_hub==2.4.0
Expand All @@ -138,121 +118,75 @@ hypothesis==6.148.3
idna==3.20
importlib_metadata==10.1.0
iniconfig==2.3.1
interegular==0.3.3
jaraco.classes==3.4.0
jaraco.context==6.1.2
jaraco.functools==4.6.0
jeepney==0.9.0
Jinja2==3.1.6
jiter==0.18.0
joblib==1.6.0
jsonpickle==4.1.4
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
keras==3.15.1
keyring==25.7.0
keyrings.google-artifactregistry-auth==1.1.2
lark==1.2.2
libclang==18.1.1
linkify-it-py==2.2.0
llguidance==0.7.30
llvmlite==0.44.0
lm-format-enforcer==0.10.12
markdown-it-py==4.2.0
MarkupSafe==3.0.4
mdit-py-plugins==0.6.1
mdurl==0.1.2
memray==1.19.3
mistral_common==1.13.1
ml_dtypes==0.6.0
mmh3==5.3.1
mock==5.2.0
more-itertools==11.2.1
mpmath==1.3.0
msgpack==1.2.4
msgspec==0.22.0
multidict==7.2.1
namex==0.1.0
networkx==3.6.1
ninja==1.13.2
nltk==3.10.4
numba==0.61.2
numpy==2.2.6
nvidia-cublas==13.4.1.3
nvidia-cublas-cu12==12.6.4.1
nvidia-cuda-cccl==13.3.4.3.1
nvidia-cuda-cupti==13.2.86
nvidia-cuda-cupti-cu12==12.6.80
nvidia-cuda-nvrtc==13.2.86
nvidia-cuda-nvrtc-cu12==12.6.77
nvidia-cuda-runtime==13.2.86
nvidia-cuda-runtime-cu12==12.6.77
nvidia-cudnn-cu12==9.5.1.17
nvidia-cudnn-cu13==9.26.0.51
nvidia-cufft==12.2.0.57
nvidia-cufft-cu12==11.3.0.4
nvidia-cufile==1.17.1.22
nvidia-cufile-cu12==1.11.1.6
nvidia-curand-cu12==10.3.7.77
nvidia-cusolver==12.2.0.11
nvidia-cusolver-cu12==11.7.1.2
nvidia-cusparse==12.7.10.12
nvidia-cusparse-cu12==12.5.4.2
nvidia-cusparselt-cu12==0.6.3
nvidia-cusparselt-cu13==0.8.1
nvidia-nccl-cu12==2.26.2
nvidia-nccl-cu13==2.30.7
nvidia-nvjitlink==13.4.92
nvidia-nvjitlink-cu12==12.6.85
nvidia-nvshmem-cu13==3.7.2
nvidia-nvtx==13.2.86
nvidia-nvtx-cu12==12.6.77
oauth2client==4.1.3
objsize==0.7.1
openai==1.107.1
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.45.2
opentelemetry-exporter-http-transport==0.66b2
opentelemetry-exporter-otlp-common==0.66b2
opentelemetry-exporter-otlp-proto-common==1.45.2
opentelemetry-exporter-otlp-proto-http==1.45.2
opentelemetry-proto==1.45.2
opentelemetry-resourcedetector-gcp==1.14.0
opentelemetry-sdk==1.45.2
opentelemetry-semantic-conventions==0.66b2
opt_einsum==3.4.0
optree==0.20.0
oracledb==26.1.0
orjson==3.13.0
outlines_core==0.2.10
packaging==26.3
pandas==2.3.3
parameterized==0.9.0
partial-json-parser==0.2.1.1.post7
pg8000==1.31.6
pillow==13.0.0
pip==26.3
platformdirs==4.14.3
pluggy==1.7.0
portalocker==4.4.2
prometheus-fastapi-instrumentator==8.1.0
prometheus_client==0.26.0
propcache==0.5.4
proto-plus==1.29.0
protobuf==6.33.6
psutil==7.2.2
psycopg2-binary==2.9.13
py-cpuinfo==9.0.0
pyarrow==25.0.1
pyasn1==0.6.5
pyasn1_modules==0.4.2
pybase64==1.5.1
pycountry==26.2.16
pycparser==3.12
pydantic==2.14.2
pydantic-extra-types==2.11.1
pydantic-settings==2.16.2
pydantic_core==2.50.2
pydot==1.4.2
Pygments==2.21.0
Expand All @@ -267,43 +201,29 @@ pytest-timeout==2.4.0
pytest-xdist==3.8.0
python-dateutil==2.9.0.post0
python-dotenv==1.2.4
python-json-logger==4.2.0
python-multipart==0.0.33
python-tds==1.17.1
pytz==2026.6
PyYAML==6.0.3
pyzmq==27.2.0
qdrant-client==1.20.0
ray==2.59.0
referencing==0.37.0
regex==2026.9.29
requests==2.34.2
requests-mock==1.12.1
rich==15.0.0
rich-toolkit==0.20.6
rignore==0.8.1
rpds-py==2026.9.1
rsa==4.9.1
safetensors==0.8.0
scikit-learn==1.7.2
scipy==1.17.1
scramp==1.5.0
SecretStorage==3.5.0
sentencepiece==0.2.2
sentry-sdk==2.73.0
setproctitle==1.3.8
setuptools==84.2.1
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sortedcontainers==2.4.0
soundfile==0.14.0
soupsieve==3.0.4
soxr==1.1.0
SQLAlchemy==2.1.6
sqlalchemy_pytds==1.0.3
sqlparse==0.6.1
starlette==1.10.0
sympy==1.14.0
tenacity==9.1.4
tensorflow==2.21.0
Expand All @@ -312,11 +232,8 @@ termcolor==3.3.0
testcontainers==4.15.0
textual==8.2.8
threadpoolctl==3.7.0
tiktoken==0.14.0
tokenizers==0.23.3
torch==2.7.1
torchaudio==2.7.1
torchvision==0.22.1
tqdm==4.70.1
transformers==5.20.2
triton==3.3.1
Expand All @@ -327,16 +244,10 @@ typing_extensions==4.16.0
tzdata==2026.6
uritemplate==4.2.0
urllib3==2.8.0
uvicorn==0.54.0
uvloop==0.23.0
virtualenv-clone==0.5.7
vllm==0.10.1.1
watchfiles==1.3.0
websockets==17.4
wheel==0.48.0
wrapt==2.5.2
xformers==0.0.31
xgrammar==0.1.21
yarl==1.25.1
zipp==4.1.2
zstandard==0.25.0
Loading
Loading