Archives

Aviz and TensorWave collaborate to improve GPU services with advanced RoCE-based AI frameworks

Aviz Networks

Aviz Networks, a leader in AI networking solutions, announces its collaboration with TensorWave, a pioneering GPU-as-a-Service provider. This collaboration focuses on smart networks that power AI by implementing RoCE (RDMA over Converged Ethernet)-based AI networks to optimize GPU-as-a-Service offerings. This implementation includes Aviz’s multi-vendor Open Network Enterprise Suite (ONES) SONiC solution.

By deploying Aviz Networks technology, TensorWave will enhance its GPU as a service offering using advanced AMD MI300 accelerators to efficiently meet growing market demands as enterprises seek to leverage GenAI, LLM and machine learning for their activities. Aviz Networks is renowned for its Networking 3.0 product suite, which has been at the forefront of AI-based network operations and management solutions.

TensorWave has quickly established itself as a leader in providing GPUs as a service, and this collaboration will only amplify its capabilities. The integration of Aviz technology will enable the management and operation of RoCE-based AI networks, crucial for managing various GPUs, DPUs and high radix switches. ONES’s unique capabilities include RoCE orchestration, real-time visibility, and threshold-based anomaly detection, making it the only agnostic AI fabric controller on the market.

Advanced RoCE orchestration and real-time anomaly detection

ONES stands out for its advanced RoCE orchestration capabilities, meticulously managing buffer settings, Priority Flow Control (PFC), and Explicit Congestion Notification (ECN). This detailed orchestration ensures that data travels efficiently across network fabrics, which is crucial for AI and machine learning applications requiring real-time processing.

Also Read: Aviz and Celestica Announce Partnership to Advance SONiC Networking Solutions 

ONES further improves network reliability through its real-time visibility and anomaly detection capabilities. It continuously monitors the network to identify and respond to anomalies, such as packet loss, preventing potential disruptions before they impact AI/AI workload execution times. ML.

Scalable features and Network Copilot™ integration

ONES’s existing feature set, which includes support for high-density platform configurations, is particularly beneficial for TensorWave-managed environments. The integration of Network Copilot™ with ONES further extends these capabilities, providing intelligent guidance and automated management functions, simplifying complex network configuration and maintenance tasks.

Darrick Horton, Managing Director of TensorWave, also comments on the collaboration: “Working with Aviz Networks will significantly strengthen our capabilities to provide superior GPU services to our customers. Aviz’s expertise in RoCE support and AI framework design will be instrumental in scaling our services to meet growing demand.

This collaboration not only highlights Aviz Networks’ commitment to providing innovative solutions, but also strengthens TensorWave’s position in the market by equipping it with cutting-edge GPU resources. With these technologies, Aviz and TensorWave are setting new standards in the industry, ensuring their customers have access to cutting-edge GPU resources optimized for the most demanding applications.

SOURCE: Businesswire