Update to suport Python 3.12 (#495)

Signed-off-by: Ryan Wolf <[email protected]>

.github/workflows/test.yml

@@ -19,7 +19,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.10"]
+        python-version: ["3.12"]
     steps:
       - uses: actions/checkout@v4
       - name: Optionally free up space on Ubuntu

Dockerfile

@@ -1,8 +1,8 @@
 # See https://github.com/rapidsai/ci-imgs for ARG options
-# NeMo Curator requires Python 3.10, Ubuntu 22.04/20.04, and CUDA 12 (or above)
+# NeMo Curator requires Python 3.12, Ubuntu 22.04/20.04, and CUDA 12 (or above)
 ARG CUDA_VER=12.5.1
 ARG LINUX_VER=ubuntu22.04
-ARG PYTHON_VER=3.10
+ARG PYTHON_VER=3.12
 ARG IMAGE_LABEL
 ARG REPO_URL
 ARG CURATOR_COMMIT
@@ -33,7 +33,7 @@ ARG CUDA_VER
 
 # Install the minimal libcu* libraries needed by NeMo Curator
 RUN conda create -y --name curator -c nvidia/label/cuda-${CUDA_VER} -c conda-forge \
-  python=3.10 \
+  python=3.12 \
   cuda-cudart \
   libcufft \
   libcublas \

README.md

@@ -69,7 +69,7 @@ This section explains how to install NeMo Curator and use the Python library, Py
 
 Before installing NeMo Curator, ensure that the following requirements are met:
 
-- Python 3.10
+- Python 3.10 or higher
 - Ubuntu 22.04/20.04
 - NVIDIA GPU (optional)
   - Volta™ or higher ([compute capability 7.0+](https://developer.nvidia.com/cuda-gpus))

docs/user-guide/image/gettingstarted.rst

@@ -12,7 +12,7 @@ Install NeMo Curator
 ---------------------
 To install the image curation modules of NeMo Curator, ensure you meet the following requirements:
 
-* Python 3.10
+* Python 3.10 or higher
 * Ubuntu 22.04/20.04
 * NVIDIA GPU
   * Volta™ or higher (compute capability 7.0+)

pyproject.toml

@@ -21,22 +21,23 @@ name = "nemo_curator"
 description = "Scalable Data Preprocessing Tool for Training Large Language Models"
 readme = { file = "README.md", content-type = "text/markdown" }
 authors = [
+    { name = "Ryan Wolf", email = "[email protected]" },
     { name = "Joseph Jennings", email = "[email protected]" },
     { name = "Mostofa Patwary", email = "[email protected]" },
     { name = "Sandeep Subramanian", email = "[email protected]" },
     { name = "Shrimai Prabhumoye", email = "[email protected]" },
     { name = "Ayush Dattagupta", email = "[email protected]" },
     { name = "Vibhu Jawa", email = "[email protected]" },
     { name = "Jiwei Liu", email = "[email protected]" },
-    { name = "Ryan Wolf", email = "[email protected]" },
     { name = "Sarah Yurick", email = "[email protected]" },
 ]
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.12",
 ]
-requires-python = ">=3.10, <3.11"
+requires-python = ">=3.10"
 dependencies = [
     "awscli>=1.22.55",
     "beautifulsoup4",