Integration of Neural Magic's SparseML and DeepSparse into Striveworks' Chariot allows customers to deploy models using only CPUs while getting GPU-like speeds
Originally published on April 3, 2023 at PRNewswire.com.
AUSTIN, Texas, April 3, 2023 — Today Striveworks and Neural Magic announced their partnership. Striveworks, a pioneer in responsible MLOps for national security and other highly regulated spaces, will integrate Neural Magic's core offerings into its Chariot MLOps platform's training and model services.
Chariot is an end-to-end MLOps software platform that provides a factory floor where data scientists, analysts, Subject Matter Experts (SMEs), and others can all work, develop, train, deploy, monitor, retrain, and redeploy custom models and custom workflows on a variety of datasets and data sources. GPUs are typically necessary to deploy models with operationally relevant inference times. However, this integration will provide Chariot users a no-code/low-code way to deploy these models to CPUs while getting GPU-like speeds.
Combining Neural Magic's SparseML libraries and DeepSparse Inference Runtime with Chariot will result in machine learning models that are smaller in size, equally as accurate, and many times more performant than even expensive hardware–accelerated compute platforms.
"Our goal at Neural Magic is to allow people to run machine learning workloads wherever they want to, without the need for specialized hardware," said Jay Marshall, VP of Business Development at Neural Magic. "Our partnership with Striveworks helps accelerate this goal by providing great performance at a lower cost on readily available CPUs on the Striveworks platform."
About Striveworks
Striveworks is a pioneer in responsible MLOps for national security and other highly regulated spaces. Striveworks' MLOps platform, Chariot, enables organizations to deploy AI/ML models at scale while maintaining full audit and remediation capabilities. Founded in 2018, Striveworks was highlighted as an exemplar in the National Security Commission for AI 2020 Final Report. For more information, visit www.striveworks.com.
About Neural Magic
Neural Magic is an AI company, born out of the Massachusetts Institute of Technology (MIT), on a mission to help customers innovate with machine learning, without added complexity or cost. While pursuing research at MIT, founders Nir Shavit and Alexander Matveev launched Neural Magic, a software-delivered AI solution, to address their frustration with the constraints of GPUs and existing hardware. Using Neural Magic's DeepSparse Inference Runtime, customers can easily deploy deep learning models on commodity CPUs with GPU-class performance. For more information, including all of Neural Magic's offerings, visit https://neuralmagic.com/ or follow @neuralmagic on Twitter, LinkedIn, and YouTube.
