Avoid default tokenization in Dask (#10398)

---------

Co-authored-by: Jiaming Yuan <jm.yuan@outlook.com>
This commit is contained in:
Richard (Rick) Zamora
2024-06-14 06:44:54 -05:00
committed by GitHub
parent 01ff2b2c29
commit dc14f98f40
5 changed files with 16 additions and 9 deletions

View File

@@ -25,7 +25,7 @@ RUN \
mamba create -y -n gpu_test -c rapidsai -c conda-forge -c nvidia \
python=3.10 cudf=$RAPIDS_VERSION_ARG* rmm=$RAPIDS_VERSION_ARG* cudatoolkit=$CUDA_VERSION_ARG \
"nccl>=${NCCL_SHORT_VER}" \
dask=2024.1.1 \
dask \
dask-cuda=$RAPIDS_VERSION_ARG* dask-cudf=$RAPIDS_VERSION_ARG* cupy \
numpy pytest pytest-timeout scipy scikit-learn pandas matplotlib wheel python-kubernetes urllib3 graphviz hypothesis \
"pyspark>=3.4.0" cloudpickle cuda-python && \

View File

@@ -28,7 +28,7 @@ RUN \
mamba create -y -n gpu_test -c rapidsai-nightly -c conda-forge -c nvidia \
python=3.10 "cudf=$RAPIDS_VERSION_ARG.*" "rmm=$RAPIDS_VERSION_ARG.*" cudatoolkit=$CUDA_VERSION_ARG \
"nccl>=${NCCL_SHORT_VER}" \
dask=2024.1.1 \
dask \
"dask-cuda=$RAPIDS_VERSION_ARG.*" "dask-cudf=$RAPIDS_VERSION_ARG.*" cupy \
numpy pytest pytest-timeout scipy scikit-learn pandas matplotlib wheel python-kubernetes urllib3 graphviz hypothesis \
"pyspark>=3.4.0" cloudpickle cuda-python && \

View File

@@ -17,8 +17,8 @@ dependencies:
- scikit-learn
- pandas
- matplotlib
- dask>=2022.6
- distributed>=2022.6
- dask
- distributed
- python-graphviz
- hypothesis>=6.46
- astroid