NVIDIA and MediaTek have expanded their long-standing semiconductor partnership across AI infrastructure, local AI computing and automotive, with NVIDIA also investing $3.5 billion in convertible bonds issued by MediaTek.
The broader collaboration brings together NVIDIA’s accelerated computing, artificial intelligence, graphics and software technologies with MediaTek’s capabilities in custom silicon, system-on-chip design, advanced packaging, interconnects, connectivity and power-efficient computing.
One of the most significant elements of the expanded relationship involves NVIDIA NVLink Fusion.
MediaTek will adopt NVLink Fusion as a foundation for customers developing custom AI accelerators, or XPUs, for hyperscale and large AI infrastructure deployments.
The platform is designed to give hyperscalers, cloud service providers and frontier AI model developers a prevalidated path for integrating custom processors into NVIDIA NVLink-connected, rack-scale AI factories.
Rather than requiring customers to develop every piece of the surrounding infrastructure themselves, MediaTek and NVIDIA plan to provide technology spanning interconnects, memory architecture, advanced packaging, manufacturing and rack-scale system integration.
Customers will be able to bring their own differentiated XPU designs to MediaTek and tailor factors such as connectivity, memory, packaging, performance and power consumption around individual workloads and infrastructure requirements.
NVLink Fusion includes the NVIDIA NVLink Fusion chiplet, which connects custom XPUs with the NVIDIA NVLink scale-up fabric using photonic or electrical interconnects.
The platform also includes NVIDIA NVLink-C2C for high-bandwidth, energy-efficient connections between XPUs, NVIDIA Rosa CPUs and compatible processors.
Another component, NVIDIA NVHBM, provides customized memory capabilities intended to increase bandwidth and energy efficiency while allowing more silicon area to be devoted to compute.
The companies are positioning the platform as a way to reduce the complexity involved in moving from custom silicon design to production-ready rack-scale AI infrastructure.
Building an accelerator represents only one portion of that process. AI systems also require coordination across multi-die architectures, high-bandwidth memory, advanced packaging, high-speed SerDes, I/O, networking, manufacturing and supply chains.
MediaTek’s participation in the broader NVLink Fusion ecosystem is intended to allow customers to combine custom processors with NVIDIA’s scale-up and scale-out infrastructure while using the NVIDIA MGX rack-scale architecture.
The expanded relationship extends beyond cloud AI infrastructure.
NVIDIA and MediaTek will continue collaborating across multiple generations of chips for NVIDIA RTX Spark and DGX Spark systems, bringing accelerated AI computing to consumer PCs, developer systems and enterprise workstations.
MediaTek previously worked with NVIDIA on the GB10 Grace Blackwell Superchip powering NVIDIA DGX Spark.
The processor combines an NVIDIA Blackwell GPU with a Grace CPU connected through NVLink-C2C, bringing significant AI computing capabilities into a compact local system.
The companies are now extending that work through NVIDIA RTX Spark as generative and agentic AI increasingly shift portions of AI inference and development from centralized data centers toward local computing devices.
Automotive represents the third major component of the expanded partnership.
NVIDIA and MediaTek plan to continue jointly developing technologies for AI-powered, software-defined vehicles.
MediaTek’s Dimensity Auto platforms already integrate NVIDIA technologies to deliver AI capabilities and NVIDIA RTX graphics for vehicle cockpits while operating alongside NVIDIA DRIVE AGX.
The companies plan to build on that architecture across future generations as vehicles incorporate increasingly sophisticated AI, graphics and physical AI capabilities.
NVIDIA’s $3.5 billion convertible bond investment in MediaTek also adds a substantial financial component to a technology relationship that now stretches from rack-scale data centers to personal computing and automobiles.
The partnership gives MediaTek a larger role within NVIDIA’s AI infrastructure ecosystem while giving NVIDIA access to MediaTek’s custom silicon, packaging, connectivity and system design capabilities across several major computing markets.
KEY QUOTES:
“AI is transforming every computing platform, from the world’s largest AI factories to the PC and the car. MediaTek is one of the world’s great semiconductor companies, with exceptional expertise in system-on-chip design, connectivity, leading performance and power efficiency.”
“Together, we’re building platforms that bring NVIDIA accelerated computing to new markets and give customers the freedom to create differentiated AI systems at enormous scale.”
Jensen Huang, Founder And CEO Of NVIDIA
“MediaTek and NVIDIA share a vision for making advanced AI computing pervasive across the technology landscape. NVIDIA’s investment strengthens a collaboration that spans cloud AI infrastructure, local AI computing and automotive in the era of physical AI.”
“By combining NVIDIA’s leadership in accelerated computing and AI software ecosystem with MediaTek’s expertise in a diverse AI technology portfolio from edge to cloud, and our leadership position in custom silicon, we can accelerate innovation for our customers.”
Rick Tsai, Vice Chairman And CEO Of MediaTek
