Feast
Make your offline data available for real-time predictions without having to build custom pipelines. Ensure data consistency between offline training and online inference, eliminating train-serve skew. Standardize data engineering workflows under one consistent framework. Teams use Feast as the foundation of their internal ML platforms. Feast doesn’t require the deployment and management of dedicated infrastructure. Instead, it reuses existing infrastructure and spins up new resources when needed. You are not looking for a managed solution and are willing to manage and maintain your own implementation. You have engineers that are able to support the implementation and management of Feast. You want to run pipelines that transform raw data into features in a separate system and integrate with it. You have unique requirements and want to build on top of an open source solution.
Learn more
NVIDIA Triton Inference Server
NVIDIA Triton™ inference server delivers fast and scalable AI in production. Open-source inference serving software, Triton inference server streamlines AI inference by enabling teams deploy trained AI models from any framework (TensorFlow, NVIDIA TensorRT®, PyTorch, ONNX, XGBoost, Python, custom and more on any GPU- or CPU-based infrastructure (cloud, data center, or edge). Triton runs models concurrently on GPUs to maximize throughput and utilization, supports x86 and ARM CPU-based inferencing, and offers features like dynamic batching, model analyzer, model ensemble, and audio streaming. Triton helps developers deliver high-performance inference aTriton integrates with Kubernetes for orchestration and scaling, exports Prometheus metrics for monitoring, supports live model updates, and can be used in all major public cloud machine learning (ML) and managed Kubernetes platforms. Triton helps standardize model deployment in production.
Learn more
Wallaroo.AI
Wallaroo facilitates the last-mile of your machine learning journey, getting ML into your production environment to impact the bottom line, with incredible speed and efficiency. Wallaroo is purpose-built from the ground up to be the easy way to deploy and manage ML in production, unlike Apache Spark, or heavy-weight containers. ML with up to 80% lower cost and easily scale to more data, more models, more complex models. Wallaroo is designed to enable data scientists to quickly and easily deploy their ML models against live data, whether to testing environments, staging, or prod. Wallaroo supports the largest set of machine learning training frameworks possible. You’re free to focus on developing and iterating on your models while letting the platform take care of deployment and inference at speed and scale.
Learn more
Xilinx
The Xilinx’s AI development platform for AI inference on Xilinx hardware platforms consists of optimized IP, tools, libraries, models, and example designs. It is designed with high efficiency and ease-of-use in mind, unleashing the full potential of AI acceleration on Xilinx FPGA and ACAP. Supports mainstream frameworks and the latest models capable of diverse deep learning tasks. Provides a comprehensive set of pre-optimized models that are ready to deploy on Xilinx devices. You can find the closest model and start re-training for your applications! Provides a powerful open source quantizer that supports pruned and unpruned model quantization, calibration, and fine tuning. The AI profiler provides layer by layer analysis to help with bottlenecks. The AI library offers open source high-level C++ and Python APIs for maximum portability from edge to cloud. Efficient and scalable IP cores can be customized to meet your needs of many different applications.
Learn more