From 8039279c832005eb6c89275f027e24c83a5e3b9b Mon Sep 17 00:00:00 2001 From: David Gardner Date: Wed, 5 Feb 2025 13:20:04 -0800 Subject: [PATCH] Remove other references to the cloud deployment guide and helm charts Update MLflow Triton Plugin description and refer to upstream repo --- README.md | 4 ---- .../guides/5_digital_fingerprinting.md | 12 +----------- docs/source/extra_info/glossary.md | 2 +- examples/digital_fingerprinting/production/README.md | 1 - 4 files changed, 2 insertions(+), 17 deletions(-) diff --git a/README.md b/README.md index 3814d1089..13d8ca3f1 100644 --- a/README.md +++ b/README.md @@ -34,8 +34,4 @@ NVIDIA Morpheus is an open AI application framework that provides cybersecurity ### Modifying Morpheus * [Contributing to Morpheus](./docs/source/developer_guide/contributing.md) - Covers building from source, making changes and contributing to Morpheus -### Deploying Morpheus -* [Morpheus Cloud Deployment Guide](./docs/source/cloud_deployment_guide.md) - Kubernetes and cloud based deployments - - Full documentation for the latest official release is available at [https://docs.nvidia.com/morpheus/](https://docs.nvidia.com/morpheus/). diff --git a/docs/source/developer_guide/guides/5_digital_fingerprinting.md b/docs/source/developer_guide/guides/5_digital_fingerprinting.md index 17e25aceb..4d829865b 100644 --- a/docs/source/developer_guide/guides/5_digital_fingerprinting.md +++ b/docs/source/developer_guide/guides/5_digital_fingerprinting.md @@ -56,7 +56,6 @@ Key Features: * Uses a model store to allow the training and inference pipelines to communicate * Organized into a docker-compose deployment for easy startup * Contains a Jupyter notebook service to ease development and debugging - * Can be deployed to Kubernetes using provided Helm charts * Uses many customized stages to maximize performance. This example is described in `examples/digital_fingerprinting/production/README.md` as well as the rest of this document. @@ -121,9 +120,7 @@ DFP in Morpheus is accomplished via two independent pipelines: training and infe ## Runtime Environment Setup ![Runtime Environment Setup](img/dfp_runtime_env.png) -DFP in Morpheus is built as an application of containerized services​ and can be run in two ways: -1. Using docker-compose for testing and development​ -1. Using helm charts for production Kubernetes deployment​ +DFP in Morpheus is built as an application of containerized services​ and can be run using `docker-compose` for testing and development​. ### Services The reference architecture is composed of the following services:​ @@ -162,12 +159,5 @@ From the `examples/digital_fingerprinting/production` dir, run: docker compose up mlflow ``` -### Running via Kubernetes​ -#### System requirements -* [Kubernetes](https://kubernetes.io/) cluster configured with GPU resources​ -* [NVIDIA GPU Operator](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/gpu-operator) installed in the cluster - -> **Note:** For GPU Requirements refer to the [Getting Started](../../getting_started.md#requirements) guide. - ## Customizing DFP For details on customizing the DFP pipeline refer to [Digital Fingerprinting (DFP) Reference](./6_digital_fingerprinting_reference.md). diff --git a/docs/source/extra_info/glossary.md b/docs/source/extra_info/glossary.md index 7fab16aef..3f2025b46 100644 --- a/docs/source/extra_info/glossary.md +++ b/docs/source/extra_info/glossary.md @@ -19,7 +19,7 @@ limitations under the License. ## MLflow Triton Plugin -A Docker container, allowing the deployment of models in [MLflow](https://mlflow.org/) to [Triton Inference Server](#triton-inference-server). Information on building this container is available in the [`models/mlflow/README.md`](https://github.com/nv-morpheus/Morpheus/blob/branch-25.02/models/mlflow/README.md) document. +[MLflow](https://mlflow.org/) plugin for deploying your models from MLflow to [Triton Inference Server](#triton-inference-server). Refer to [`mlflow-triton-plugin`](https://github.com/triton-inference-server/server/tree/main/deploy/mlflow-triton-plugin) for more information. ## module A Morpheus module is a type of work unit that can be utilized in the Morpheus stage and can be registered to a MRC segment module registry. Modules are beneficial when there is a possibility for the work-unit to be reused. diff --git a/examples/digital_fingerprinting/production/README.md b/examples/digital_fingerprinting/production/README.md index c9c9d5d18..cc1ba41c6 100644 --- a/examples/digital_fingerprinting/production/README.md +++ b/examples/digital_fingerprinting/production/README.md @@ -24,7 +24,6 @@ Key Features: * Uses a model store to allow the training and inference pipelines to communicate * Organized into a `docker compose` deployment for easy startup * Contains a Jupyter notebook service to ease development and debugging - * Can be deployed to Kubernetes using provided Helm charts * Uses many customized stages to maximize performance. ## Building and Running via `docker compose`