NVIDIA · rgsl888prabhu · Jun 6, 2025 · Jun 6, 2025 · Jun 6, 2025 · Jun 6, 2025
diff --git a/README.md b/README.md
@@ -63,6 +63,8 @@ For CUDA 12.x:
 pip install --extra-index-url=https://pypi.nvidia.com cuopt-server-cu12==25.5.* cuopt-sh-client==25.5.* nvidia-cuda-runtime-cu12==12.8.*
 ```
 
+Development wheels are available as nightlies, please update `--extra-index-url` to `https://pypi.anaconda.org/rapidsai-wheels-nightly/simple/` to install latest nightly packages.
+
 ### Conda
 
 cuOpt can be installed with conda (via [miniforge](https://github.com/conda-forge/miniforge)) from the `nvidia` channel:
@@ -74,19 +76,22 @@ Users who are used to conda env based workflows would benefit with conda package
 For CUDA 12.x:
 ```bash
 conda install -c rapidsai -c conda-forge -c nvidia \
-    cuopt-server=25.05 cuopt-sh-client=25.05 python=3.12 cuda-version=12.8
+    cuopt-server=25.05.* cuopt-sh-client=25.05.* python=3.12 cuda-version=12.8
 ```
 
 We also provide [nightly Conda packages](https://anaconda.org/rapidsai-nightly) built from the HEAD
-of our latest development branch.
+of our latest development branch. Just replace `-c rapidsai` with `-c rapidsai-nightly`.
 
 ### Container 
 
 Users can pull the cuOpt container from the NVIDIA container registry.
 
 ```bash
-docker pull nvidia/cuopt:25.5.0-cuda12.8-py312 
+docker pull nvidia/cuopt:latest-cuda12.8-py312 
 ```
+
+Note: The ``latest`` tag is the latest stable release of cuOpt. If you want to use a specific version, you can use the ``<version>-cuda12.8-py312`` tag. For example, to use cuOpt 25.5.0, you can use the ``25.5.0-cuda12.8-py312`` tag. Please refer to `cuOpt dockerhub page <https://hub.docker.com/r/nvidia/cuopt>`_ for the list of available tags.
+
 More information about the cuOpt container can be found [here](https://docs.nvidia.com/cuopt/user-guide/latest/cuopt-server/quick-start.html#container-from-docker-hub).
 
 Users who are using cuOpt for quick testing or research can use the cuOpt container. Alternatively, users who are planning to plug cuOpt as a service in their workflow can quickly start with the cuOpt container. But users are required to build security layers around the service to safeguard the service from untrusted users.

@@ -17,6 +17,10 @@ For CUDA 12.x:
     pip install --extra-index-url=https://pypi.nvidia.com cuopt-cu12==25.5.* nvidia-cuda-runtime-cu12==12.8.*
 
 
+.. note::
+   For development wheels which are available as nightlies, please update `--extra-index-url` to `https://pypi.anaconda.org/rapidsai-wheels-nightly/simple/`. 
+
+
 Conda
 -----
 
@@ -29,6 +33,9 @@ For CUDA 12.x:
     conda install -c rapidsai -c conda-forge -c nvidia \
         cuopt=25.05.* python=3.12 cuda-version=12.8
 
+.. note::
+   For development conda packages which are available as nightlies, please update `-c rapidsai` to `-c rapidsai-nightly`.
+
 
 Container
 ---------
@@ -37,13 +44,16 @@ NVIDIA cuOpt is also available as a container from Docker Hub:
 
 .. code-block:: bash
 
-    docker pull nvidia/cuopt:25.5.0-cuda12.8-py312
+    docker pull nvidia/cuopt:latest-cuda12.8-py312
+
+.. note::
+   The ``latest`` tag is the latest stable release of cuOpt. If you want to use a specific version, you can use the ``<version>-cuda12.8-py312`` tag. For example, to use cuOpt 25.5.0, you can use the ``25.5.0-cuda12.8-py312`` tag. Please refer to `cuOpt dockerhub page <https://hub.docker.com/r/nvidia/cuopt>`_ for the list of available tags. 
 
 The container includes both the Python API and self-hosted server components. To run the container:
 
 .. code-block:: bash
 
-    docker run --gpus all -it --rm nvidia/cuopt:25.5.0-cuda12.8-py312 
+    docker run --gpus all -it --rm nvidia/cuopt:latest-cuda12.8-py312 
 
 This will start an interactive session with cuOpt pre-installed and ready to use.
 

@@ -14,6 +14,8 @@ For CUDA 12.x:
 
     pip install --extra-index-url=https://pypi.nvidia.com cuopt-server-cu12==25.5.* cuopt-sh-client==25.5.* nvidia-cuda-runtime-cu12==12.8.*
 
+.. note::
+   For development wheels which are available as nightlies, please update `--extra-index-url` to `https://pypi.anaconda.org/rapidsai-wheels-nightly/simple/`.
 
 Conda
 -----
@@ -27,6 +29,9 @@ For CUDA 12.x:
     conda install -c rapidsai -c conda-forge -c nvidia \
         cuopt-server=25.05.* cuopt-sh-client=25.05.* python=3.12 cuda-version=12.8
 
+.. note::
+   For development conda packages which are available as nightlies, please update `-c rapidsai` to `-c rapidsai-nightly`.
+
 
 Container from Docker Hub
 -------------------------
@@ -35,13 +40,16 @@ NVIDIA cuOpt is also available as a container from Docker Hub:
 
 .. code-block:: bash
 
-    docker pull nvidia/cuopt:25.5.0-cuda12.8-py312
+    docker pull nvidia/cuopt:latest-cuda12.8-py312
+
+.. note::
+   The ``latest`` tag is the latest stable release of cuOpt. If you want to use a specific version, you can use the ``<version>-cuda12.8-py312`` tag. For example, to use cuOpt 25.5.0, you can use the ``25.5.0-cuda12.8-py312`` tag. Please refer to `cuOpt dockerhub page <https://hub.docker.com/r/nvidia/cuopt>`_ for the list of available tags. 
 
 The container includes both the Python API and self-hosted server components. To run the container:
 
 .. code-block:: bash
 
-    docker run --gpus all -it --rm -p 8000:8000 -e CUOPT_SERVER_PORT=8000 nvidia/cuopt:25.5.0-cuda12.8-py312 /bin/bash -c "python3 -m cuopt_server.cuopt_service"
+    docker run --gpus all -it --rm -p 8000:8000 -e CUOPT_SERVER_PORT=8000 nvidia/cuopt:latest-cuda12.8-py312 /bin/bash -c "python3 -m cuopt_server.cuopt_service"
 
 .. note::
    Make sure you have the NVIDIA Container Toolkit installed on your system to enable GPU support in containers. See the `installation guide <https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html>`_ for details.

@@ -60,6 +60,16 @@ Command Line Interface (cuopt-cli)
 
    Command Line Interface Overview <cuopt-cli/index.rst>
 
+========================================
+Third-Party Modeling Languages
+========================================
+.. toctree::
+   :maxdepth: 4
+   :caption: Third-Party Modeling Languages
+   :name: Third-Party Modeling Languages
+
+   thirdparty_modeling_languages/index.rst 
+
 =============
 Resources
 =============

@@ -118,6 +118,10 @@ cuOpt supports the following APIs:
    - `Linear Programming (LP) - Server <cuopt-server/quick-start.html>`_
    - `Mixed Integer Linear Programming (MILP) - Server <cuopt-server/quick-start.html>`_
    - `Routing (TSP, VRP, and PDP) - Server <cuopt-server/quick-start.html>`_
+- Third-party modeling languages
+   - `AMPL <https://www.ampl.com/>`_
+   - `PuLP <https://pypi.org/project/PuLP/>`_
+
 
 ==================================
 Installation Options

@@ -7,6 +7,12 @@ Availability
 
 The LP solver can be accessed in the following ways:
 
+- **Third-Party Modeling Languages**: cuOpt's LP and MILP solver can be called directly from the following third-party modeling languages. This allows you to leverage GPU acceleration while maintaining your existing optimization workflow in these modeling languages.
+
+  Supported modeling languages:
+   -  AMPL
+   -  PuLP 
+
 - **C API**: A native C API that provides direct low-level access to cuOpt's LP capabilities, enabling integration into any application or system that can interface with C.
 
 - **As a Self-Hosted Service**: cuOpt's LP solver can be deployed as a in your own infrastructure, enabling you to maintain full control while integrating it into your existing systems.

@@ -48,7 +48,7 @@ Solution File
 Note: the default value is ``""`` and no solution file is written.
 
 User Problem File
-^^^^^^^^^^^^^^^^
+^^^^^^^^^^^^^^^^^
 ``CUOPT_USER_PROBLEM_FILE`` controls the name of a file where cuOpt should write the user problem.
 
 Note: the default value is ``""`` and no user problem file is written.

@@ -7,6 +7,12 @@ Availability
 
 The MILP solver can be accessed in the following ways:
 
+- **Third-Party Modeling Languages**: cuOpt's LP and MILP solver can be called directly from the following third-party modeling languages. This allows you to leverage GPU acceleration while maintaining your existing optimization workflow in these modeling languages.
+
+  Currently supported solvers:
+   - AMPL
+   - PuLP 
+
 - **C API**: A native C API that provides direct low-level access to cuOpt's MILP solver, enabling integration into any application or system that can interface with C.
 
 - **As a Self-Hosted Service**: cuOpt's MILP solver can be deployed in your own infrastructure, enabling you to maintain full control while integrating it into your existing systems.

@@ -0,0 +1,17 @@
+===============================
+Third-Party Modeling Languages
+===============================
+
+
+--------------------------
+AMPL Support
+--------------------------
+
+AMPL can be used with near zero code changes: simply switch to cuOpt as a solver to solve linear and mixed-integer programming problems. Please refer to the `AMPL documentation <https://www.ampl.com/>`_ for more information.
+
+--------------------------
+PuLP Support
+--------------------------
+
+PuLP can be used with near zero code changes: simply switch to cuOpt as a solver to solve linear and mixed-integer programming problems.
+Please refer to the `PuLP documentation <https://pypi.org/project/PuLP/>`_ for more information. Also, see the example notebook in the `cuopt-examples <https://github.com/NVIDIA/cuopt-examples>`_ repository.