NVIDIA · eordentlich · Jul 10, 2023 · Jun 23, 2023 · Jul 6, 2023 · Jul 7, 2023
diff --git a/ci/Dockerfile b/ci/Dockerfile
@@ -35,7 +35,7 @@ RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-py38_4.10.3-Linu
     && conda init
 
 # install cuML
-ARG CUML_VER=23.04
+ARG CUML_VER=23.06
 RUN conda install -c conda-forge mamba && \
-    mamba install -y -c rapidsai -c nvidia -c conda-forge cuml=$CUML_VER python=3.8 cuda-toolkit=11.5 \
+    mamba install -y -c rapidsai -c nvidia -c conda-forge cuml=$CUML_VER python=3.9 cuda-toolkit=11.5 \
     && mamba clean --all -f -y
diff --git a/docker/Dockerfile b/docker/Dockerfile
@@ -88,7 +88,7 @@ RUN wget --quiet \
 # install cuDF dependency, Fall back to use cudf 22.04 due to issue:
 # https://github.com/NVIDIA/spark-rapids-ml/issues/73
 ARG CONDA_CUDF_VER=22.04
-RUN conda install -c rapidsai -c conda-forge cudf=$CONDA_CUDF_VER python=3.8 -y
+RUN conda install -c rapidsai -c conda-forge cudf=$CONDA_CUDF_VER python=3.9 -y
 
 # Note: the raft verion is fixed to 22.12, do not modify it when updating the spark-rapids-ml version.
 #       newer versions may fail the build process due to API incompatibility.
@@ -98,7 +98,7 @@ ENV RAFT_PATH=/raft
 
 ### END OF CACHE ###
 
-#ARG RAPIDS_ML_VER=23.04
+#ARG RAPIDS_ML_VER=23.06
 #RUN git clone -b branch-$RAPIDS_ML_VER https://github.com/NVIDIA/spark-rapids-ml.git
 COPY . /spark-rapids-ml
 WORKDIR /spark-rapids-ml/jvm

diff --git a/docker/Dockerfile.pip b/docker/Dockerfile.pip
@@ -18,7 +18,7 @@ ARG CUDA_VERSION=11.8.0
 FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
 
 ARG PYSPARK_VERSION=3.3.1
-ARG RAPIDS_VERSION=23.4.0
+ARG RAPIDS_VERSION=23.6.0
 
 # Install packages to build spark-rapids-ml
 RUN apt-get update -y \

diff --git a/docker/Dockerfile.python b/docker/Dockerfile.python
@@ -17,7 +17,7 @@
 ARG CUDA_VERSION=11.5.2
 FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
 
-ARG CUML_VERSION=23.04
+ARG CUML_VERSION=23.06
 
 # Install packages to build spark-rapids-ml
 RUN apt update -y \
@@ -38,7 +38,7 @@ RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-py38_4.10.3-Linu
 
 # install cuML
 
-RUN conda install -y -c rapidsai -c nvidia -c conda-forge python=3.8 cuda-toolkit=11.5 cuml=$CUML_VERSION \
+RUN conda install -y -c rapidsai -c nvidia -c conda-forge python=3.9 cuda-toolkit=11.5 cuml=$CUML_VERSION \
     && conda clean --all -f -y
 
 # install python dependencies

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -9,7 +9,7 @@
 project = 'spark-rapids-ml'
 copyright = '2023, NVIDIA'
 author = 'NVIDIA'
-release = '23.4.0'
+release = '23.6.0'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

diff --git a/notebooks/aws-emr/init-bootstrap-action.sh b/notebooks/aws-emr/init-bootstrap-action.sh
@@ -8,7 +8,7 @@ sudo chmod a+rwx -R /sys/fs/cgroup/devices
 sudo yum install -y gcc openssl-devel bzip2-devel libffi-devel tar gzip wget make mysql-devel
 sudo bash -c "wget https://www.python.org/ftp/python/3.9.9/Python-3.9.9.tgz && tar xzf Python-3.9.9.tgz && cd Python-3.9.9 && ./configure --enable-optimizations && make altinstall"
 
-RAPIDS_VERSION=23.4.0
+RAPIDS_VERSION=23.6.0
 
 # install scikit-learn 
 sudo /usr/local/bin/pip3.9 install scikit-learn

diff --git a/notebooks/databricks/init-pip-cuda-11.8.sh b/notebooks/databricks/init-pip-cuda-11.8.sh
@@ -1,10 +1,10 @@
 #!/bin/bash
 # set portion of path below after /dbfs/ to dbfs zip file location
 SPARK_RAPIDS_ML_ZIP=/dbfs/path/to/zip/file
-# IMPORTANT: specify RAPIDS_VERSION fully 23.4.0 and not 23.4
-# also RAPIDS_VERSION (python) fields should omit any leading 0 in month/minor field (i.e. 23.4.0 and not 23.04.0)
-# while SPARK_RAPIDS_VERSION (jar) should have leading 0 in month/minor (e.g. 23.04.0 and not 23.4.0)
-RAPIDS_VERSION=23.4.0
+# IMPORTANT: specify RAPIDS_VERSION fully 23.6.0 and not 23.6
+# also RAPIDS_VERSION (python) fields should omit any leading 0 in month/minor field (i.e. 23.6.0 and not 23.06.0)
+# while SPARK_RAPIDS_VERSION (jar) should have leading 0 in month/minor (e.g. 23.06.0 and not 23.6.0)
+RAPIDS_VERSION=23.6.0
 SPARK_RAPIDS_VERSION=23.04.0
 
 curl -L https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/${SPARK_RAPIDS_VERSION}/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar -o /databricks/jars/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar

diff --git a/notebooks/dataproc/README.md b/notebooks/dataproc/README.md
@@ -27,7 +27,7 @@ If you already have a Dataproc account, you can run the example notebooks on a D
 - Create a cluster with at least two single-gpu workers.  **Note**: in addition to the initialization script from above, this also uses the standard [initialization actions](https://github.com/GoogleCloudDataproc/initialization-actions) for installing the GPU drivers and RAPIDS:
   ```
   export CUDA_VERSION=11.8
-  export RAPIDS_VERSION=23.4
+  export RAPIDS_VERSION=23.6
 
   gcloud dataproc clusters create $USER-spark-rapids-ml \
   --image-version=2.0.29-ubuntu18 \

diff --git a/notebooks/dataproc/spark_rapids_ml.sh b/notebooks/dataproc/spark_rapids_ml.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-RAPIDS_VERSION=23.4.0
+RAPIDS_VERSION=23.6.0
 
 # patch existing packages
 mamba install "llvmlite<0.40,>=0.39.0dev0" "numba>=0.56.2"

diff --git a/python/README.md b/python/README.md
@@ -8,9 +8,9 @@ For simplicity, the following instructions just use Spark local mode, assuming a
 
 First, install RAPIDS cuML per [these instructions](https://rapids.ai/start.html).
 ```bash
-conda create -n rapids-23.04 \
+conda create -n rapids-23.06 \
     -c rapidsai -c nvidia -c conda-forge \
-    cuml=23.04 python=3.8 cudatoolkit=11.5
+    cuml=23.06 python=3.9 cudatoolkit=11.5
 ```
 
 **Note**: while testing, we recommend using conda or docker to simplify installation and isolate your environment while experimenting.  Once you have a working environment, you can then try installing directly, if necessary.
@@ -19,7 +19,7 @@ conda create -n rapids-23.04 \
 
 Once you have the conda environment, activate it and install the required packages.
 ```bash
-conda activate rapids-23.04
+conda activate rapids-23.06
 
 # for development access to notebooks, tests, and benchmarks
 git clone --branch main https://github.com/NVIDIA/spark-rapids-ml.git

diff --git a/python/benchmark/databricks/init-pip-cuda-11.8.sh b/python/benchmark/databricks/init-pip-cuda-11.8.sh
@@ -2,10 +2,10 @@
 # set portion of path below after /dbfs/ to dbfs zip file location
 SPARK_RAPIDS_ML_ZIP=/dbfs/path/to/spark-rapids-ml.zip
 BENCHMARK_ZIP=/dbfs/path/to/benchmark.zip
-# IMPORTANT: specify rapids fully 23.4.0 and not 23.4
-# also RAPIDS_VERSION (python) fields should omit any leading 0 in month/minor field (i.e. 23.4.0 and not 23.04.0)
-# while SPARK_RAPIDS_VERSION (jar) should have leading 0 in month/minor (e.g. 23.04.0 and not 23.4.0)
-RAPIDS_VERSION=23.4.0
+# IMPORTANT: specify rapids fully 23.6.0 and not 23.6
+# also RAPIDS_VERSION (python) fields should omit any leading 0 in month/minor field (i.e. 23.6.0 and not 23.06.0)
+# while SPARK_RAPIDS_VERSION (jar) should have leading 0 in month/minor (e.g. 23.06.0 and not 23.6.0)
+RAPIDS_VERSION=23.6.0
 SPARK_RAPIDS_VERSION=23.04.0
 
 curl -L https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/${SPARK_RAPIDS_VERSION}/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar -o /databricks/jars/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar

diff --git a/python/benchmark/dataproc/init_benchmark.sh b/python/benchmark/dataproc/init_benchmark.sh
@@ -8,7 +8,7 @@ function get_metadata_attribute() {
   /usr/share/google/get_metadata_value "attributes/${attribute_name}" || echo -n "${default_value}"
 }
 
-RAPIDS_VERSION=$(get_metadata_attribute rapids-version 23.4.0)
+RAPIDS_VERSION=$(get_metadata_attribute rapids-version 23.6.0)
 
 # patch existing packages
 mamba install "llvmlite<0.40,>=0.39.0dev0" "numba>=0.56.2"

diff --git a/python/benchmark/dataproc/start_cluster.sh b/python/benchmark/dataproc/start_cluster.sh
@@ -14,7 +14,7 @@ fi
 
 BENCHMARK_HOME=${BENCHMARK_HOME:-${GCS_BUCKET}/benchmark}
 CUDA_VERSION=${CUDA_VERSION:-11.8}
-RAPIDS_VERSION=${RAPIDS_VERSION:-23.4.0}
+RAPIDS_VERSION=${RAPIDS_VERSION:-23.6.0}
 
 gpu_args=$(cat <<EOF
 --master-accelerator type=nvidia-tesla-t4,count=1
@@ -51,7 +51,7 @@ if [[ $? == 0 ]]; then
 else
     set -x
     gcloud dataproc clusters create ${cluster_name} \
-    --image-version=2.0.29-ubuntu18 \
+    --image-version=2.1-ubuntu18 \
     --region ${COMPUTE_REGION} \
     --master-machine-type n1-standard-16 \
     --num-workers 2 \

diff --git a/python/pyproject.toml b/python/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "spark-rapids-ml"
-version = "23.4.0"
+version = "23.6.0"
 authors = [
   { name="Jinfeng Li", email="[email protected]" },
   { name="Bobby Wang", email="[email protected]" },

diff --git a/python/src/spark_rapids_ml/__init__.py b/python/src/spark_rapids_ml/__init__.py
@@ -13,4 +13,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-__version__ = "23.4.0"
+__version__ = "23.6.0"