Merge branch 'development' into 'master'

Development

See merge request dsop/opensource/triton-inference-server/server!15

.gitlab-ci.yml

+include:
+  - project: 'ironbank-tools/ironbank-pipeline'
+    file: '/templates/default.yaml'
+    ref: "large-s3-upload"
+
+variables:
+  YAML_LINT_DISABLED: "true"
+  DOCKERFILE_LINT_DISABLED: "true"
+  WL_TARGET_BRANCH: "pipeline-test-project"

Dockerfile

+ARG BASE_REGISTRY=registry1.dsop.mil
+ARG BASE_IMAGE="redhat/ubi/ubi8"
+ARG BASE_TAG="8.3"
+
+FROM ${BASE_REGISTRY}/${BASE_IMAGE}:${BASE_TAG}
+
+ARG VERSION=23.03
+
+RUN useradd -u 1818 triton
+
+ENV CUDA_VERSION 11.2.1
+
+RUN dnf upgrade && dnf -y install pkg-config libgomp libpng python38 && dnf clean all
+
+# nvidia-docker 1.0
+RUN echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf && \
+    echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf
+
+#ENV
+ENV PATH /usr/local/nvidia/bin:/usr/local/cuda/bin:${PATH}
+ENV LD_LIBRARY_PATH /usr/local/nvidia/lib:/usr/local/nvidia/lib64:/opt/tritonserver/lib
+
+#Link
+RUN ln -s cuda-11.2 /usr/local/cuda
+
+# nvidia-container-runtime
+ENV NVIDIA_VISIBLE_DEVICES all
+ENV NVIDIA_DRIVER_CAPABILITIES compute,utility
+ENV NVIDIA_REQUIRE_CUDA "cuda>=11.2 brand=tesla,driver>=418,driver<419 brand=tesla,driver>=440,driver<441 driver>=450,driver<451"
+
+#Args
+ARG TARBALL1=OCV.tar
+ARG TARBALL2=rpms.tar.gz
+ARG TARBALL6=libtensorflow_cc.so.1.tar.gz
+ARG TARBALL7=libtensorflow_cc.so.tar.gz
+ARG TARBALL8=libtensorflow_framework.so.1.tar.gz
+ARG TARBALL9=libtensorflow_framework.so.tar.gz
+ARG TARBALL10=libtensorflow_triton.so.1.tar.gz
+ARG TARBALL11=libtensorflow_triton.so.tar.gz
+ARG TARBALL12=libtriton_tensorflow1.so.tar.gz
+ARG TARBALL13=tritonserverwobe.tar.gz
+
+ARG TARBALLN1=nvidia.rpms.tar
+
+COPY ["${TARBALL1}", "/"]
+
+COPY ["${TARBALLN1}", "${TARBALL13}", "${TARBALL2}","/opt/"]
+
+WORKDIR /
+RUN tar -xvf ./${TARBALL1} && rm -fv ./${TARBALL1}
+
+WORKDIR /opt
+
+#Untar
+RUN tar -xvf ./${TARBALLN1} && rm -fv ./${TARBALLN1}
+RUN tar -zxf ./${TARBALL2} && rm -fv ./${TARBALL2}
+RUN tar -zxf ./${TARBALL13} && rm -fv ./${TARBALL13}
+
+COPY ["${TARBALL6}", "${TARBALL7}", "${TARBALL8}", "${TARBALL9}", \
+       "${TARBALL10}", "${TARBALL11}", "${TARBALL12}", "/opt/tritonserver/backends/tensorflow1/"]
+
+WORKDIR tritonserver/backends/tensorflow1
+
+RUN tar -zxf ./${TARBALL6} && rm -fv ./${TARBALL6}
+RUN tar -zxf ./${TARBALL7} && rm -fv ./${TARBALL7}
+RUN tar -zxf ./${TARBALL8} && rm -fv ./${TARBALL8}
+RUN tar -zxf ./${TARBALL9} && rm -fv ./${TARBALL9}
+RUN tar -zxf ./${TARBALL10} && rm -fv ./${TARBALL10}
+RUN tar -zxf ./${TARBALL11} && rm -fv ./${TARBALL11}
+RUN tar -zxf ./${TARBALL12} && rm -fv ./${TARBALL12}
+
+
+#Move the tf backend parts to their spot
+#RUN mv libtensorflow_cc.so.1 libtensorflow_cc.so libtensorflow_framework.so.1 \
+# libtensorflow_framework.so libtensorflow_triton.so.1 libtensorflow_triton.so \
+# libtriton_tensorflow1.so LICENSE.tensorflow tritonserver/backends/tensorflow1/
+
+WORKDIR /opt/baserpms
+
+#re2
+RUN rpm -i re2-20190801-1.el8.x86_64.rpm
+
+ENV NCCL_VERSION 2.8.4
+ENV LIBRARY_PATH /usr/local/cuda/lib64/stubs
+
+ENV CUDNN_VERSION 8.1.0.77
+
+WORKDIR /opt/nvidia.rpms
+RUN rpm --nodeps -i *.rpm
+
+WORKDIR /
+
+#RUN rm -r usr/local/cuda-11.2/libnvvp
+
+RUN mkdir /models
+
+#RUN ln -s /usr/local/cuda-11.2/targets/x86_64-linux/lib/stubs/libnvidia-ml.so \
+# /usr/local/cuda-11.2/targets/x86_64-linux/lib/stubs/libnvidia-ml.so.1
+
+USER triton
+
+EXPOSE 8000
+EXPOSE 8001
+EXPOSE 8002
+#
+ENTRYPOINT ["/opt/tritonserver/bin/tritonserver", "--strict-model-config=false", "--model-repository", "/models"]
+
+HEALTHCHECK --timeout=30s CMD curl -fs http://localhost:8000/v2 || exit 1
\ No newline at end of file

LICENSE

+
+Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+ * Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+ * Neither the name of NVIDIA CORPORATION nor the names of its
+   contributors may be used to endorse or promote products derived
+   from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
\ No newline at end of file

README.md

-# <application name>
+<!--
+# Copyright (c) 2018-2021, NVIDIA CORPORATION. All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#  * Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+#  * Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#  * Neither the name of NVIDIA CORPORATION nor the names of its
+#    contributors may be used to endorse or promote products derived
+#    from this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+-->
 
-Project template for all Iron Bank container repositories.
\ No newline at end of file
+[![License](https://img.shields.io/badge/License-BSD3-lightgrey.svg)](https://opensource.org/licenses/BSD-3-Clause)
+
+# Triton Inference Server
+
+**LATEST RELEASE: You are currently on the master branch which tracks
+under-development progress towards the next release. The latest
+release of the Triton Inference Server is 2.6.0 and is available on
+branch
+[r20.12](https://github.com/triton-inference-server/server/tree/r20.12).**
+
+Triton Inference Server provides a cloud and edge inferencing solution
+optimized for both CPUs and GPUs. Triton supports an HTTP/REST and
+GRPC protocol that allows remote clients to request inferencing for
+any model being managed by the server. For edge deployments, Triton is
+available as a shared library with a C API that allows the full
+functionality of Triton to be included directly in an
+application.
+
+The current release of the Triton Inference Server is 2.6.0 and
+corresponds to the 20.12 release of the tritonserver container on
+[NVIDIA GPU Cloud (NGC)](https://ngc.nvidia.com). The branch for this
+release is
+[r20.12](https://github.com/triton-inference-server/server/tree/r20.12).
+
+## Features
+
+* [Multiple deep-learning
+  frameworks](https://github.com/triton-inference-server/backend). Triton
+  can manage any number and mix of models (limited by system disk and
+  memory resources). Triton supports TensorRT, TensorFlow GraphDef,
+  TensorFlow SavedModel, ONNX, and PyTorch TorchScript model
+  formats. Both TensorFlow 1.x and TensorFlow 2.x are
+  supported. Triton also supports TensorFlow-TensorRT and
+  ONNX-TensorRT integrated models.
+
+* [Concurrent model
+  execution](docs/architecture.md#concurrent-model-execution). Multiple
+  models (or multiple instances of the same model) can run
+  simultaneously on the same GPU or on multiple GPUs.
+
+* [Dynamic batching](docs/architecture.md#models-and-schedulers). For
+  models that support batching, Triton implements multiple scheduling
+  and batching algorithms that combine individual inference requests
+  together to improve inference throughput. These scheduling and
+  batching decisions are transparent to the client requesting
+  inference.
+
+* [Extensible
+  backends](https://github.com/triton-inference-server/backend). In
+  addition to deep-learning frameworks, Triton provides a *backend
+  API* that allows Triton to be extended with any model execution
+  logic implemented in
+  [Python](https://github.com/triton-inference-server/python_backend)
+  or
+  [C++](https://github.com/triton-inference-server/backend/blob/main/README.md#triton-backend-api),
+  while still benefiting from the CPU and GPU support, concurrent
+  execution, dynamic batching and other features provided by Triton.
+
+* [Model pipelines](docs/architecture.md#ensemble-models). Triton
+  *ensembles* represents a pipeline of one or more models and the
+  connection of input and output tensors between those models. A
+  single inference request to an ensemble will trigger the execution
+  of the entire pipeline.
+
+* [HTTP/REST and GRPC inference
+  protocols](docs/inference_protocols.md) based on the community
+  developed [KFServing
+  protocol](https://github.com/kubeflow/kfserving/tree/master/docs/predict-api/v2).
+
+* A [C API](docs/inference_protocols.md#c-api) allows Triton to be
+  linked directly into your application for edge and other in-process
+  use cases.
+
+* [Metrics](docs/metrics.md) indicating GPU utilization, server
+  throughput, and server latency. The metrics are provided in
+  Prometheus data format.
+
+## Documentation
+
+**The master branch documentation tracks the upcoming,
+under-development release and so may not be accurate for the current
+release of Triton. See the [r20.12
+documentation](https://github.com/triton-inference-server/server/tree/r20.12#documentation)
+for the current release.**
+
+[Triton Architecture](docs/architecture.md) gives a high-level
+overview of the structure and capabilities of the inference
+server. There is also an [FAQ](docs/faq.md). Additional documentation
+is divided into [*user*](#user-documentation) and
+[*developer*](#developer-documentation) sections. The *user*
+documentation describes how to use Triton as an inference solution,
+including information on how to configure Triton, how to organize and
+configure your models, how to use the C++ and Python clients, etc. The
+*developer* documentation describes how to build and test Triton and
+also how Triton can be extended with new functionality.
+
+The Triton [Release
+Notes](https://docs.nvidia.com/deeplearning/triton-inference-server/release-notes/index.html)
+and [Support
+Matrix](https://docs.nvidia.com/deeplearning/dgx/support-matrix/index.html)
+indicate the required versions of the NVIDIA Driver and CUDA, and also
+describe supported GPUs.
+
+### User Documentation
+
+- [QuickStart](docs/quickstart.md)
+    - [Install](docs/quickstart.md#install-triton-docker-image)
+    - [Run](docs/quickstart.md#run-triton)
+- [Model Repository](docs/model_repository.md)
+- [Model Configuration](docs/model_configuration.md)
+- [Model Management](docs/model_management.md)
+- [Custom Operations](docs/custom_operations.md)
+- [Client Libraries](docs/client_libraries.md)
+- [Client Examples](docs/client_examples.md)
+- [Optimization](docs/optimization.md)
+    - [Model Analyzer](docs/model_analyzer.md)
+    - [Performance Analyzer](docs/perf_analyzer.md)
+- [Metrics](docs/metrics.md)
+
+The [quickstart](docs/quickstart.md) walks you through all the steps
+required to install and run Triton with an example image
+classification model and then use an example client application to
+perform inferencing using that model. The quickstart also demonstrates
+how [Triton supports both GPU systems and CPU-only
+systems](docs/quickstart.md#run-triton).
+
+The first step in using Triton to serve your models is to place one or
+more models into a [model
+repository](docs/model_repository.md). Optionally, depending on the type
+of the model and on what Triton capabilities you want to enable for
+the model, you may need to create a [model
+configuration](docs/model_configuration.md) for the model.  If your
+model has [custom operations](docs/custom_operations.md) you will need
+to make sure they are loaded correctly by Triton.
+
+After you have your model(s) available in Triton, you will want to
+send inference and other requests to Triton from your *client*
+application. The [Python and C++ client
+libraries](docs/client_libraries.md) provide
+[APIs](docs/client_libraries.md#client-library-apis) to simplify this
+communication. There are also a large number of [client
+examples](docs/client_examples.md) that demonstrate how to use the
+libraries.  You can also send HTTP/REST requests directly to Triton
+using the [HTTP/REST JSON-based
+protocol](docs/inference_protocols.md#httprest-and-grpc-protocols) or
+[generate a GRPC client for many other
+languages](docs/client_libraries.md).
+
+Understanding and [optimizing performance](docs/optimization.md) is an
+important part of deploying your models. The Triton project provides
+the [Performance Analyzer](docs/perf_analyzer.md) and the [Model
+Analyzer](docs/model_analyzer.md) to help your optimization
+efforts. Specifically, you will want to optimize [scheduling and
+batching](docs/architecture.md#models-and-schedulers) and [model
+instances](docs/model_configuration.md#instance-groups) appropriately
+for each model. You may also want to consider [ensembling multiple
+models and pre/post-processing](docs/architecture.md#ensemble-models)
+into a pipeline. In some cases you may find [individual inference
+request trace data](docs/trace.md) useful when optimizing. A
+[Prometheus metrics endpoint](docs/metrics.md) allows you to visualize
+and monitor aggregate inference metrics.
+
+NVIDIA publishes a number of [deep learning
+examples](https://github.com/NVIDIA/DeepLearningExamples) that use
+Triton.
+
+As part of your deployment strategy you may want to [explicitly manage
+what models are available by loading and unloading
+models](docs/model_management.md) from a running Triton server. If you
+are using Kubernetes for deployment a simple example of how to [deploy
+Triton using Kubernetes and Helm](deploy/single_server/README.md) may
+be helpful.
+
+The [version 1 to version 2 migration
+information](docs/v1_to_v2.md) is helpful if you are moving to
+version 2 of Triton from previously using version 1.
+
+### Developer Documentation
+
+- [Build](docs/build.md)
+- [Protocols and APIs](docs/inference_protocols.md).
+- [Backends](https://github.com/triton-inference-server/backend)
+- [Repository Agents](docs/repository_agents.md)
+- [Test](docs/test.md)
+
+Triton can be [built using
+Docker](docs/build.md#building-triton-with-docker) or [built without
+Docker](docs/build.md#building-triton-without-docker). After building
+you should [test Triton](docs/test.md).
+
+Starting with the r20.10 release, it is also possible to [create a
+Docker image containing a customized Triton](docs/compose.md) that
+contains only a subset of the backends.
+
+The Triton project also provides [client libraries for Python and
+C++](docs/client_libraries.md) that make it easy to communicate with
+the server. There are also a large number of [example
+clients](docs/client_examples.md) that demonstrate how to use the
+libraries. You can also develop your own clients that directly
+communicate with Triton using [HTTP/REST or GRPC
+protocols](docs/inference_protocols.md). There is also a [C
+API](docs/inference_protocols.md) that allows Triton to be linked
+directly into your application.
+
+A [Triton backend](https://github.com/triton-inference-server/backend)
+is the implementation that executes a model. A backend can interface
+with a deep learning framework, like PyTorch, TensorFlow, TensorRT or
+ONNX Runtime; or it can interface with a data processing framework
+like [DALI](https://github.com/triton-inference-server/dali_backend);
+or you can extend Triton by [writing your own
+backend](https://github.com/triton-inference-server/backend) in either
+[C/C++](https://github.com/triton-inference-server/backend/blob/main/README.md#triton-backend-api)
+or
+[Python](https://github.com/triton-inference-server/python_backend).
+
+A [Triton repository agent](docs/repository_agents.md) extends Triton
+with new functionality that operates when a model is loaded or
+unloaded. You can introduce your own code to perform authentication,
+decryption, conversion, or similar operations when a model is loaded.
+
+## Papers and Presentation
+
+* [Maximizing Deep Learning Inference Performance with NVIDIA Model
+  Analyzer](https://developer.nvidia.com/blog/maximizing-deep-learning-inference-performance-with-nvidia-model-analyzer/).
+
+* [High-Performance Inferencing at Scale Using the TensorRT Inference
+  Server](https://developer.nvidia.com/gtc/2020/video/s22418).
+
+* [Accelerate and Autoscale Deep Learning Inference on GPUs with
+  KFServing](https://developer.nvidia.com/gtc/2020/video/s22459).
+
+* [Deep into Triton Inference Server: BERT Practical Deployment on
+  NVIDIA GPU](https://developer.nvidia.com/gtc/2020/video/s21736).
+
+* [Maximizing Utilization for Data Center Inference with TensorRT
+  Inference Server](https://on-demand-gtc.gputechconf.com/gtcnew/sessionview.php?sessionName=s9438-maximizing+utilization+for+data+center+inference+with+tensorrt+inference+server).
+
+* [NVIDIA TensorRT Inference Server Boosts Deep Learning
+  Inference](https://devblogs.nvidia.com/nvidia-serves-deep-learning-inference/).
+
+* [GPU-Accelerated Inference for Kubernetes with the NVIDIA TensorRT
+  Inference Server and
+  Kubeflow](https://www.kubeflow.org/blog/nvidia_tensorrt/).
+
+## Contributing
+
+Contributions to Triton Inference Server are more than welcome. To
+contribute make a pull request and follow the guidelines outlined in
+[CONTRIBUTING.md](CONTRIBUTING.md). If you have a backend, client,
+example or similar contribution that is not modifying the core of
+Triton, then you should file a PR in the [contrib
+repo](https://github.com/triton-inference-server/contrib).
+
+## Reporting problems, asking questions
+
+We appreciate any feedback, questions or bug reporting regarding this
+project. When help with code is needed, follow the process outlined in
+the Stack Overflow (https://stackoverflow.com/help/mcve)
+document. Ensure posted examples are:
+
+* minimal – use as little code as possible that still produces the
+  same problem
+
+* complete – provide all parts needed to reproduce the problem. Check
+  if you can strip external dependency and still show the problem. The
+  less time we spend on reproducing problems the more time we have to
+  fix it
+
+* verifiable – test the code you're about to provide to make sure it
+  reproduces the problem. Remove all other problems that are not
+  related to your request/question.
\ No newline at end of file

hardening_manifest.yaml

+---
+apiVersion: v1
+
+name: "opensource/triton-inference-server/server"
+
+tags:
+  - "20.03"
+  - "latest"
+
+args:
+  BASE_IMAGE: "redhat/ubi/ubi8"
+  BASE_TAG: "8.3"
+
+# Docker image labels
+labels:
+  # Name of the image
+  org.opencontainers.image.title: "triton-inference-server"
+  # Human-readable description of the software packaged in the image
+  org.opencontainers.image.description: "Triton Inference Server provides a data center inference solution optimized for NVIDIA GPUs."
+  # License(s) under which contained software is distributed
+  org.opencontainers.image.licenses: "Contact nvidia-compute-license-questions@nvidia.com"
+  # URL to find more information on the image
+  org.opencontainers.image.url: "https://ngc.nvidia.com/catalog/containers/nvidia:tritonserver"
+  # Name of the distributing entity, organization or individual
+  org.opencontainers.image.vendor: "NVIDIA"
+  # Authoritative version of the software
+  org.opencontainers.image.version: "20.03"
+  # Keywords to help with search (ex. "cicd,gitops,golang")
+  mil.dso.ironbank.image.keywords: "triton, inference"
+  # This value can be "opensource" or "commercial"
+  mil.dso.ironbank.image.type: "opensource"
+  # Product the image belongs to for grouping multiple images
+  mil.dso.ironbank.product.name: "triton-inference-server"
+
+resources:
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/baserpms.tar.gz"
+    filename: "rpms.tar.gz"
+    validation:
+      type: "sha256"
+      value: "f89e7923559a92b63480c428c9189f41f5910921bbb96fe77d28fc43a77466e0"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtensorflow_cc.so.1.tar.gz"
+    filename: "libtensorflow_cc.so.1.tar.gz"
+    validation:
+      type: "sha256"
+      value: "05e0b0815183009b51096c4e3547f8cb8eb18af84d3ae3de7f3885b263e4ec92"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtensorflow_cc.so.tar.gz"
+    filename: "libtensorflow_cc.so.tar.gz"
+    validation:
+      type: "sha256"
+      value: "7c9b47a9e50c9ade04d82aa835a0e7399e63c895145da94ebb15021b2388accb"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtensorflow_framework.so.1.tar.gz"
+    filename: "libtensorflow_framework.so.1.tar.gz"
+    validation:
+      type: "sha256"
+      value: "71f615ea586ef406cb35ba1b8231f15bcf5ad5245fab4230965964567ef0b882"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtensorflow_framework.so.tar.gz"
+    filename: "libtensorflow_framework.so.tar.gz"
+    validation:
+      type: "sha256"
+      value: "20b02f7e2f21523c56c0a0955c0f1acab1d951d5629aa795e7a74975e96075ca"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtensorflow_triton.so.1.tar.gz"
+    filename: "libtensorflow_triton.so.1.tar.gz"
+    validation:
+      type: "sha256"
+      value: "3a61ac78b5cea7835981b3ff0dbdb437aba2a9a01330d13005cb6d4e7f8ae91c"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtensorflow_triton.so.tar.gz"
+    filename: "libtensorflow_triton.so.tar.gz"
+    validation:
+      type: "sha256"
+      value: "511334f58cfd7185943a204c5fe5817833175fb44fe16cf890bb0f4088d1c918"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/libtriton_tensorflow1.so.tar.gz"
+    filename: "libtriton_tensorflow1.so.tar.gz"
+    validation:
+      type: "sha256"
+      value: "436e06f34d7aa0e59278abda0e0018bd91975b535789d8674c2ee555e1fc5d76"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/tritonserverwobe.tar.gz"
+    filename: "tritonserverwobe.tar.gz"
+    validation:
+      type: "sha256"
+      value: "a14c2b8ff2495299f99ccce9f58f53b75e06a54496e298dba7960d0646598851"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/nvidia.rpms.tar"
+    filename: "nvidia.rpms.tar"
+    validation:
+      type: "sha256"
+      value: "66801d2eef84fe087bc9fcc4d25d17785352572365b3f9ec969729ba3027b777"
+  - url: "https://iron-bank-tars.s3-us-gov-west-1.amazonaws.com/OCV.tar"
+    filename: "OCV.tar"
+    validation:
+      type: "sha256"
+      value: "02a342f9eb90f09338f0cffa19378befd09e9e0ed24da93b239c65d40ad87cf6"
+
+maintainers:
+  - name: "Daniel Mumpton"
+    username: "daniel.mumpton"
+    email: "daniel.mumpton.ctr@us.af.mil"
+  - name: "Doug Barnum"
+    username: "doug.barnum"
+    email: "doug.barnum@techngs.com"
+  - name: "Andrew Simonetta"
+    username: "andrew.simonetta"
+    email: "andrew.simonetta@techngs.com"