Vybium, develops European AI/ML accelerators based on the Stream Computing NPU IP
Vybium is a fabless semiconductor startup building RISC-V-based solutions that will support European Digital Strategic Sovereignty & Semiconductor self-reliance
VIENNA, AUSTRIA, July 8, 2024 -- Last week, the RISC-V Summit Europe in Munich introduced Vybium, an emerging European startup dedicated to AI Accelerator products.
Vybium aims to enhance European digital strategic autonomy through its innovative RISC-V-based solutions.
Vybium operates as a fabless semiconductor company, currently in stealth mode. Founded by VRULL (Austria) and Software Ecosystem Solutions (Albania), Vybium focuses on developing AI-accelerated solutions leveraging the RISC-V ISA across various verticals.
To expedite its market entry, Vybium emphasizes the development of industry-leading AI/ML solutions with comprehensive end-to-end software support.
To swiftly achieve best-in-class performance, Vybium has licensed NPU IP from Stream Computing, enhancing it with new data types, sparsity support, and higher-bandwidth memory solutions.
"Vybium is committed to delivering products developed in Europe that reflect the European perspective, providing end-to-end RISC-V solutions tailored to the needs of European industrial companies," said Dr. Philipp Tomsich. "The rapid growth of AI/ML across applications has shifted customer priorities. We address these needs promptly with our production-proven NPU IP from Stream Computing."
Andy Mei, CEO of Stream Computing, added, "Empowering Vybium to develop their silicon by innovating on our NPU IP accelerates the development of European AI/ML accelerators to compete with Nvidia. This shared technology base supports broader, open-source software enablement, creating a true win-win."
Vybium's initial product line will focus on AI/ML accelerator cards, aiming to compete with Nvidia's A100 family. Subsequent designs will integrate RISC-V general-purpose compute with AI/ML for embedded, industrial, and edge applications, following the initial focus on datacenter, cloud, and enterprise AI/ML acceleration.
Positioned as a formidable alternative to industry leaders, Vybium leverages VRULL's software expertise and Stream Computing's advanced NPU IP. This strategic partnership enables Vybium to deliver cutting-edge RISC-V AI/ML technologies with superior performance. As Vybium advances, it will play a critical role in driving European semiconductor innovation, enhancing digital independence, and providing robust solutions for industrial and enterprise applications across Europe and beyond.
About Vybium:
Vybium is a European semiconductor startup specializing in AI Accelerator products. Focused on delivering cutting-edge RISC-V-based AI/ML solutions, Vybium aims to contribute to Europe's mission for strategic digital autonomy and semiconductor innovation in industrial and enterprise applications.
Vybium is currently operating in stealth mode.
Related Semiconductor IP
- NPU
- RISC-V-Based, Open Source AI Accelerator for the Edge
- NPU IP for Embedded ML
- Highly scalable inference NPU IP for next-gen AI applications
- Scalable Edge NPU IP for Generative AI
Related News
- OPENEDGES AI Accelerator (NPU) & Memory Subsystem IP licensed for Eyenix AI-powered surveillance camera chipset
- SiPearl Collaborates with NVIDIA on Enabling Accelerated Computing Solutions with European Microprocessor
- Andes Technology and TetraMem Collaborate to Build Groundbreaking AI Accelerator Chip with Analog In-Memory Computing
- Neurxcore Introduces Innovative NPU Product Line for AI Inference Applications, Powered by NVIDIA Deep Learning Accelerator Technology
Latest News
- Year-to-Date Global Semiconductor Sales Top $1 Trillion Through August
- Xiphera launches nQrux® Root of Trust with Post-Quantum Cryptography
- Skyechip Joins Rapidus Core Ecosystem, Bringing Advanced Silicon IP For AI and HPC to Japan's 2nm Platform
- GUC Monthly Sales Report – September 2026
- Rapidus Unveils “Rapidus CORE”, New Global Ecosystem Framework Supporting the Development and Mass Production of Cutting-Edge Semiconductors