update versions to 25.08 (#972)

eordentlich · web-flow · commit dcb55dae4486 · 2025-08-13T23:25:05.000-07:00
update all package version references to 25.08
update rapids dependencies to released 25.08
update spark-rapids from 25.04 to 25.06

Signed-off-by: Erik Ordentlich &lt;eordentlich@gmail.com&gt;
diff --git a/ci/Dockerfile b/ci/Dockerfile
@@ -48,5 +48,5 @@ RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86
 
 # install cuML
 ARG CUML_VER=25.08
-RUN conda install -y -c rapidsai-nightly -c conda-forge -c nvidia cuml=$CUML_VER cuvs=$CUML_VER python=3.10 cuda-version=12.0 numpy~=1.0 \
+RUN conda install -y -c rapidsai -c conda-forge -c nvidia cuml=$CUML_VER cuvs=$CUML_VER python=3.10 cuda-version=12.0 numpy~=1.0 \
     && conda clean --all -f -y
diff --git a/docker/Dockerfile.pip b/docker/Dockerfile.pip
@@ -18,7 +18,7 @@ ARG CUDA_VERSION=12.0.1
 FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
 
 ARG PYSPARK_VERSION=3.3.1
-ARG RAPIDS_VERSION=25.6.0
+ARG RAPIDS_VERSION=25.8.0
 ARG ARCH=amd64
 #ARG ARCH=arm64
 
@@ -47,9 +47,9 @@ RUN apt-get update -y \
 # install RAPIDS
 # using ~= pulls in micro version patches
 RUN pip install --no-cache-dir \
-    cudf-cu11~=${RAPIDS_VERSION} \
-    cuml-cu11~=${RAPIDS_VERSION} \
-    cuvs-cu11~=${RAPIDS_VERSION} \
+    cudf-cu12~=${RAPIDS_VERSION} \
+    cuml-cu12~=${RAPIDS_VERSION} \
+    cuvs-cu12~=${RAPIDS_VERSION} \
     numpy~=1.0 \
     --extra-index-url=https://pypi.nvidia.com
 
diff --git a/docker/Dockerfile.python b/docker/Dockerfile.python
@@ -17,7 +17,7 @@
 ARG CUDA_VERSION=12.0.1
 FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
 
-ARG CUML_VERSION=25.06
+ARG CUML_VERSION=25.08
 
 # ubuntu22
 RUN sed -i -e 's|http://archive.ubuntu.com/ubuntu|https://archive.ubuntu.com/ubuntu|g' \
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -23,7 +23,7 @@
 project = 'spark-rapids-ml'
 copyright = '2025, NVIDIA'
 author = 'NVIDIA'
-release = '25.06.0'
+release = '25.08.0'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
diff --git a/jvm/README.md b/jvm/README.md
@@ -50,10 +50,10 @@ including setting up the server and running client-side tests.
 To start the Spark Connect server with Spark Rapids ML support, follow these steps:
 
 ```shell
-conda activate rapids-25.06  # from spark-rapids-ml installation
+conda activate rapids-25.08  # from spark-rapids-ml installation
 export SPARK_HOME=<directory where spark was installed above>
 export PYSPARK_PYTHON=$(which python)
-export PLUGIN_JAR=$(pip show spark-rapids-ml | grep Location: | cut -d ' ' -f 2 )/spark_rapids_ml/jars/com.nvidia.rapids.ml-25.06.0.jar
+export PLUGIN_JAR=$(pip show spark-rapids-ml | grep Location: | cut -d ' ' -f 2 )/spark_rapids_ml/jars/com.nvidia.rapids.ml-25.08.0.jar
 $SPARK_HOME/sbin/start-connect-server.sh --master local[*] \
   --jars $PLUGIN_JAR \
   --conf spark.driver.memory=20G
@@ -107,7 +107,7 @@ mvn clean package -DskipTests
 if you would like to compile the plugin and run the unit tests, install `spark-rapids-ml` python package and its dependencies per the above instructions and run the following command:
 
 ``` shell
-conda activate rapids-25.06
+conda activate rapids-25.08
 export PYSPARK_PYTHON=$(which python)
 mvn clean package
 ```
diff --git a/jvm/pom.xml b/jvm/pom.xml
@@ -21,7 +21,7 @@
 
     <groupId>com.nvidia.rapids</groupId>
     <artifactId>ml</artifactId>
-    <version>25.06.0</version>
+    <version>25.08.0</version>
     <packaging>jar</packaging>
 
     <properties>
diff --git a/notebooks/aws-emr/init-bootstrap-action.sh b/notebooks/aws-emr/init-bootstrap-action.sh
@@ -27,7 +27,7 @@ sudo bash -c "wget https://www.python.org/ftp/python/3.10.9/Python-3.10.9.tgz &&
 tar xzf Python-3.10.9.tgz && cd Python-3.10.9 && \
 ./configure --enable-optimizations && make altinstall"
 
-RAPIDS_VERSION=25.6.0
+RAPIDS_VERSION=25.8.0
 
 sudo /usr/local/bin/pip3.10 install --upgrade pip
 
diff --git a/notebooks/databricks/README.md b/notebooks/databricks/README.md
@@ -27,7 +27,7 @@ If you already have a Databricks account, you can run the example notebooks on a
       spark.task.resource.gpu.amount 0.125
       spark.databricks.delta.preview.enabled true
       spark.python.worker.reuse true
-      spark.executorEnv.PYTHONPATH /databricks/jars/rapids-4-spark_2.12-25.04.0.jar:/databricks/spark/python
+      spark.executorEnv.PYTHONPATH /databricks/jars/rapids-4-spark_2.12-25.06.0.jar:/databricks/spark/python
       spark.sql.execution.arrow.maxRecordsPerBatch 100000
       spark.plugins com.nvidia.spark.SQLPlugin
       spark.locality.wait 0s
diff --git a/notebooks/databricks/init-pip-cuda-12.0.sh b/notebooks/databricks/init-pip-cuda-12.0.sh
@@ -18,8 +18,8 @@ set -ex
 # IMPORTANT: specify RAPIDS_VERSION fully 23.10.0 and not 23.10
 # also in general, RAPIDS_VERSION (python) fields should omit any leading 0 in month/minor field (i.e. 23.8.0 and not 23.08.0)
 # while SPARK_RAPIDS_VERSION (jar) should have leading 0 in month/minor (e.g. 23.08.2 and not 23.8.2)
-RAPIDS_VERSION=25.6.0
-SPARK_RAPIDS_VERSION=25.04.0
+RAPIDS_VERSION=25.8.0
+SPARK_RAPIDS_VERSION=25.06.0
 
 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}-cuda12.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
@@ -31,7 +31,7 @@ If you already have a Dataproc account, you can run the example notebooks on a D
   If you wish to enable [no-import-change](../README.md#no-import-change) UX for the cluster, change the `spark-rapids-ml-no-import-enabled` metadata value to `1` in the command.  The initialization script `spark_rapids_ml.sh` checks this metadata value and modifies the run time accordingly.
 
   ```
-  export RAPIDS_VERSION=25.6.0
+  export RAPIDS_VERSION=25.8.0
 
   gcloud dataproc clusters create $USER-spark-rapids-ml \
   --image-version=2.2-ubuntu22 \
diff --git a/notebooks/dataproc/spark_rapids_ml.sh b/notebooks/dataproc/spark_rapids_ml.sh
@@ -15,7 +15,7 @@
 
 set -ex
 
-RAPIDS_VERSION=25.6.0
+RAPIDS_VERSION=25.8.0
 
 
 # install cudf and cuml
diff --git a/python/README.md b/python/README.md
@@ -20,9 +20,9 @@ For simplicity, the following instructions just use Spark local mode, assuming a
 
 First, install RAPIDS cuML per [these instructions](https://rapids.ai/start.html).   Example for CUDA Toolkit 12.0:
 ```bash
-conda create -n rapids-25.06 \
+conda create -n rapids-25.08 \
     -c rapidsai -c conda-forge -c nvidia \
-    cuml=25.06 cuvs=25.06 python=3.10 cuda-version=12.0 numpy~=1.0
+    cuml=25.08 cuvs=25.08 python=3.10 cuda-version=12.0 numpy~=1.0
 ```
 
 **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.
@@ -31,7 +31,7 @@ conda create -n rapids-25.06 \
 
 Once you have the conda environment, activate it and install the required packages.
 ```bash
-conda activate rapids-25.06
+conda activate rapids-25.08
 
 ## 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/gpu_etl_cluster_spec.sh b/python/benchmark/databricks/gpu_etl_cluster_spec.sh
@@ -23,7 +23,7 @@ cat <<EOF
         "spark.task.cpus": "1",
         "spark.databricks.delta.preview.enabled": "true",
         "spark.python.worker.reuse": "true",
-        "spark.executorEnv.PYTHONPATH": "/databricks/jars/rapids-4-spark_2.12-25.04.0.jar:/databricks/spark/python",
+        "spark.executorEnv.PYTHONPATH": "/databricks/jars/rapids-4-spark_2.12-25.06.0.jar:/databricks/spark/python",
         "spark.sql.files.minPartitionNum": "2",
         "spark.sql.execution.arrow.maxRecordsPerBatch": "10000",
         "spark.executor.cores": "8",
diff --git a/python/benchmark/databricks/init-pip-cuda-12.0.sh b/python/benchmark/databricks/init-pip-cuda-12.0.sh
@@ -19,10 +19,10 @@ BENCHMARK_ZIP=/dbfs/path/to/benchmark.zip
 # IMPORTANT: specify rapids fully 23.10.0 and not 23.10
 # also, in general, RAPIDS_VERSION (python) fields should omit any leading 0 in month/minor field (i.e. 23.8.0 and not 23.08.0)
 # while SPARK_RAPIDS_VERSION (jar) should have leading 0 in month/minor (e.g. 23.08.2 and not 23.8.2)
-RAPIDS_VERSION=25.6.0
-SPARK_RAPIDS_VERSION=25.04.0
+RAPIDS_VERSION=25.8.0
+SPARK_RAPIDS_VERSION=25.06.0
 
-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}-cuda11.jar -o /databricks/jars/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar
+curl -L https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/${SPARK_RAPIDS_VERSION}/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}-cuda12.jar -o /databricks/jars/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar
 
 # install cudatoolkit 12.0 via runfile approach
 wget https://developer.download.nvidia.com/compute/cuda/12.0.1/local_installers/cuda_12.0.1_525.85.12_linux.run
@@ -38,11 +38,9 @@ ln -s /usr/local/cuda-12.0 /usr/local/cuda
 
 # install cudf and cuml
 # using ~= pulls in micro version patches
-/databricks/python/bin/pip install cudf-cu11~=${RAPIDS_VERSION} \
-    cuml-cu11~=${RAPIDS_VERSION} \
-    cuvs-cu11~=${RAPIDS_VERSION} \
-    pylibraft-cu11~=${RAPIDS_VERSION} \
-    rmm-cu11~=${RAPIDS_VERSION} \
+/databricks/python/bin/pip install cudf-cu12~=${RAPIDS_VERSION} \
+    cuml-cu12~=${RAPIDS_VERSION} \
+    cuvs-cu12~=${RAPIDS_VERSION} \
     --extra-index-url=https://pypi.nvidia.com
 
 # install spark-rapids-ml
diff --git a/python/benchmark/dataproc/init_benchmark.sh b/python/benchmark/dataproc/init_benchmark.sh
@@ -22,7 +22,7 @@ function get_metadata_attribute() {
   /usr/share/google/get_metadata_value "attributes/${attribute_name}" || echo -n "${default_value}"
 }
 
-RAPIDS_VERSION=$(get_metadata_attribute rapids-version 25.6.0)
+RAPIDS_VERSION=$(get_metadata_attribute rapids-version 25.8.0)
 
 
 # install cudf and cuml
diff --git a/python/pyproject.toml b/python/pyproject.toml
@@ -14,7 +14,7 @@
 
 [project]
 name = "spark-rapids-ml"
-version = "25.06.0"
+version = "25.08.0"
 authors = [
   { name="Jinfeng Li", email="jinfeng@nvidia.com" },
   { name="Bobby Wang", email="bobwang@nvidia.com" },
diff --git a/python/run_benchmark.sh b/python/run_benchmark.sh
@@ -149,7 +149,7 @@ fi
 spark_rapids_confs=""
 if [[ $cluster_type == "gpu_etl" ]]
 then
-SPARK_RAPIDS_VERSION=25.04.0
+SPARK_RAPIDS_VERSION=25.06.0
 rapids_jar=${rapids_jar:-rapids-4-spark_2.12-$SPARK_RAPIDS_VERSION.jar}
 if [ ! -f $rapids_jar ]; then
     echo "downloading spark rapids jar"
diff --git a/python/src/spark_rapids_ml/__init__.py b/python/src/spark_rapids_ml/__init__.py
@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-__version__ = "25.06.0"
+__version__ = "25.08.0"
 
 import pandas as pd
 import pyspark
diff --git a/python/tests/test_umap.py b/python/tests/test_umap.py
@@ -649,7 +649,7 @@ def test_umap_sample_fraction(gpu_number: int) -> None:
 def test_umap_build_algo(gpu_number: int, metric: str) -> None:
 
     n_rows = 10000
-    # cuml 25.06 UMAP is unstable for low dimensions
+    # cuml 25.08 UMAP is unstable for low dimensions
     n_cols = 100
     random_state = 42
 
