Rapt AI is collaborating with AMD to enhance AI workload management and inference performance.
This partners will integrate Rapt’s intelligent workload automation platform with AMD’s Instinct MI300X, MI325X, and upcoming MI350 series GPUs, to provide customers with a scalable, high-performance and cost-effective solution for deploying AI applications across on-premises and multi-cloud environments.
The combined solution from Rapt and AMD ensures maximum GPU utilisation to improve AI inference and training efficiency.
Rapt’s platform streamlines GPU management to allow data scientists to focus on innovation rather than infrastructure configuration. It supports diverse GPU environments through a single instance, ensuring maximum infrastructure flexibility.
The collaboration also boosts inference performance and scalability by intelligently optimising job density and resource allocation on AMD Instinct GPUs.
Rapt’s auto-scaling capabilities ensure efficient resource use based on demand, reducing latency and maximising cost efficiency. Optimised for AMD Instinct GPUs, the platform delivers immediate performance benefits. Ongoing collaboration will drive further optimisations in areas such as GPU scheduling and memory utilisation.
“Our collaboration with Rapt AI combines the cutting-edge capabilities of AMD Instinct GPUs with Rapt’s intelligent workload automation, enabling customers to achieve greater efficiency, flexibility, and cost savings across their AI infrastructure,” said Negin Oliver, Corporate Vice President of Business Development for the Data Centre GPU Business at AMD.
“Collaboration with AMD allows us to further enhance our platform, optimising it for the powerful AMD Instinct GPUs. This joint solution is set to transform AI infrastructure management, driving better performance, cost efficiency, and faster time to value for our mutual customers,” said Charlie Leeming, CEO of Rapt.
Entelechy Asia 