TorchServe

TorchServe is a flexible and easy to use tool for serving and scaling PyTorch models in production.

Requires python >= 3.8

curl http://127.0.0.1:8080/predictions/bert -T input.txt

🚀 Quick start with TorchServe

# Install dependencies
# cuda is optional
python ./ts_scripts/install_dependencies.py --cuda=cu111

# Latest release
pip install torchserve torch-model-archiver torch-workflow-archiver

# Nightly build
pip install torchserve-nightly torch-model-archiver-nightly torch-workflow-archiver-nightly

Getting started guide

🐳 Quick Start with Docker

# Latest release
docker pull pytorch/torchserve

# Nightly build
docker pull pytorch/torchserve-nightly

Refer to torchserve docker for details.

⚡ Why TorchServe

• Model Management API: multi model management with optimized worker to model allocation
• Inference API: REST and gRPC support for batched inference
• TorchServe Workflows: deploy complex DAGs with multiple interdependent models
• Default way to serve PyTorch models in
  • Kubeflow
  • MLflow
  • Sagemaker
  • Kserve
  • Vertex AI
• Export your model for optimized inference. Torchscript out of the box, ORT, IPEX, TensorRT, FasterTransformer
• Performance Guide: builtin support to optimize, benchmark and profile PyTorch and TorchServe performance
• Expressive handlers: An expressive handler architecture that makes it trivial to support inferencing for your usecase with many supported out of the box
• Metrics API: out of box support for system level metrics with Prometheus exports, custom metrics and PyTorch profiler support

🤔 How does TorchServe work

• Model Server for PyTorch Documentation: Full documentation
• TorchServe internals: How TorchServe was built
• Contributing guide: How to contribute to TorchServe

🏆 Highlighted Examples

• 🤗 HuggingFace Transformers
• Model parallel inference
• MultiModal models with MMF combining text, audio and video
• Dual Neural Machine Translation for a complex workflow DAG

For more examples

🤓 Learn More

https://pytorch.org/serve

🫂 Contributing

We welcome all contributions!

To learn more about how to contribute, see the contributor guide here.

📰 News

• Grokking Intel CPU PyTorch performance from first principles: a TorchServe case study
• Case Study: Amazon Ads Uses PyTorch and AWS Inferentia to Scale Models for Ads Processing
• Optimize your inference jobs using dynamic batch inference with TorchServe on Amazon SageMaker
• Using AI to bring children's drawings to life
• 🎥 Model Serving in PyTorch
• Evolution of Cresta’s machine learning architecture: Migration to AWS and PyTorch
• 🎥 Explain Like I’m 5: TorchServe
• 🎥 How to Serve PyTorch Models with TorchServe
• How to deploy PyTorch models on Vertex AI
• Quantitative Comparison of Serving Platforms
• Efficient Serverless deployment of PyTorch models on Azure
• Deploy PyTorch models with TorchServe in Azure Machine Learning online endpoints
• Dynaboard moving beyond accuracy to holistic model evaluation in NLP
• A MLOps Tale about operationalising MLFlow and PyTorch
• Operationalize, Scale and Infuse Trust in AI Models using KFServing
• How Wadhwani AI Uses PyTorch To Empower Cotton Farmers
• TorchServe Streamlit Integration
• Dynabench aims to make AI models more robust through distributed human workers
• Announcing TorchServe

💖 All Contributors

Made with contrib.rocks.

⚖️ Disclaimer

This repository is jointly operated and maintained by Amazon, Meta and a number of individual contributors listed in the CONTRIBUTORS file. For questions directed at Meta, please send an email to opensource@fb.com. For questions directed at Amazon, please send an email to torchserve@amazon.com. For all other questions, please open up an issue in this repository here.

TorchServe acknowledges the Multi Model Server (MMS) project from which it was derived