One-day event brings together builders of open AI infrastructure to share real-world performance, deployment, and scaling strategies
SAN FRANCISCO, CA / ACCESS Newswire / March 31, 2026 / TensorWave today announced Beyond Summit (formerly Beyond CUDA), a one-day event taking place on April 8, 2026 in San Francisco, bringing together engineers, researchers, and infrastructure leaders shaping the future of AI compute.
Originally launched as Beyond CUDA, the event has evolved into Beyond Summit to reflect a broader industry shift: production AI is no longer defined by a single vendor, architecture, or cloud. As teams scale real-world workloads, they are increasingly adopting open, high-performance infrastructure to improve flexibility, resilience, and cost efficiency.
"AI infrastructure is entering a new phase where choice matters," said Jeff Tatarchuk, Co-founder and Chief Growth Officer of TensorWave. "Beyond Summit is about the teams actually building and running these systems, sharing what works, what doesn't, and how to operate AI in production outside the walled gardens of Nvidia."
The event will feature a lineup of leading voices across AI and infrastructure, including Ashish Vaswani (Essential AI), Dylan Patel (SemiAnalysis), Mathias Lechner (Liquid AI), Anush Elangovan (AMD), Mark Saroufim (PyTorch / GPUmode), and Gregory Diamos (ScalarLM), alongside additional speakers from across the ecosystem.
Designed for technical practitioners, Beyond Summit will focus on real-world deployment and performance. Sessions will explore topics including:
Optimizing workloads on AMD Instinct GPUs
Scaling distributed training
Improving performance under real production conditions
Navigating portability across frameworks like PyTorch and JAX
Cost models and capacity planning
Emerging approaches beyond transformer-based systems
The event is supported by a group of partners advancing open AI infrastructure, including AMD as Platinum Sponsor, Sanmina Corporation as Gold Sponsor, and Credo as Silver Sponsor, all contributing to the growing ecosystem enabling alternative, high-performance compute solutions.
Beyond Summit builds on the strong reception of TensorWave's inaugural Beyond CUDA event, which convened engineers and researchers seeking practical alternatives to traditional AI infrastructure approaches. As demand for AI compute continues to accelerate, the event reflects a broader industry movement toward more open, scalable, and production-ready systems.
Beyond Summit will convene the broader AI infrastructure community, from engineers and researchers to founders and technical leaders, focused on building systems that can evolve as quickly as the technology itself.
Registration is now open, with additional speaker announcements to follow. Apply to register here.
About TensorWave
TensorWave is the AI cloud purpose-built for performance. Powered exclusively by AMD Instinct Series GPUs, TensorWave delivers high-bandwidth, memory-optimized infrastructure that scales with the most demanding training and inference workloads. Backed by more than $166 million in funding from investors including Magnetar, AMD Ventures, and Nexus Venture Partners, TensorWave operates one of the world's largest all-AMD GPU clouds and is expanding rapidly to meet global demand. For more information, please visit tensorwave.com.
Contact:
Tensorwave@pancomm.com
SOURCE: TensorWave
View the original press release on ACCESS Newswire:
https://www.accessnewswire.com/newsroom/en/computers-technology-and-internet/tensorwave-introduces-%22beyond-summit-%22-expanding-its-flagship-ai-1153530
