In today’s world, real-time decision-making is critical — and that’s where Edge AI delivers. Unlike traditional cloud-based AI, Edge AI processes data directly where it’s generated — on devices, machines, and sensors — enabling instant insights, lower latency, enhanced privacy, and reduced bandwidth costs. From autonomous vehicles to smart factories, Edge AI empowers industries to operate faster, smarter, and more securely. Tyr is built to unlock the full potential of Edge AI, delivering data-center-class performance in an ultra-efficient, compact form — bringing advanced AI capabilities to the very edge of your operations.
Our Tyr family of processors delivers up to 1,600 Tflops of Edge AI performance—approaching data center levels of compute power, but with dramatically lower energy consumption. This unlocks new possibilities in areas that once seemed out of reach for edge computing.
Experience AI at the edge—faster, safer, and smarter.
Edge AI is reshaping industries by enabling fast, secure, and intelligent decision-making—right where it’s needed most. Here’s how it’s making an impact:
Edge AI processes real-time sensor data to create an immediate understanding of the vehicle’s surroundings. This insight powers critical decisions and actions within milliseconds—essential for safe navigation. With data cycles as fast as ~30ms, vehicles require ultra-low latency and high compute performance. Edge AI is the key—and Generative AI is beginning to play a role in enabling smarter navigation and prediction systems.
Robots are increasingly autonomous, operating in dynamic environments where immediate reactions are crucial. A striking example is space robotics like the Mars rover, which must function without relying on Earth-based decisions. In factory settings, robots must react in milliseconds for tasks like precision handling or quality control. Federated learning allows these robots to continually adapt, updating models based on local conditions without needing constant connectivity.
In modern industrial plants, 2,000+ machines can generate over 2,200 TB of data per month. Transmitting all that data to the cloud? Impractical. Edge AI enables local data filtering, compression, and analysis—right at the machine—driving faster insights and lower costs.
Examples include:
HQ
13 rue Jeanne Braconnier
Immeuble Le Pasteur
92360 Meudon-La-Forêt
France
Asia
Taipei
Taiwan
Japan
Tokyo
Japan
Korea
Seoul
Korea
USA
San Diego, CA
USA
Unmatched Performance at the Edge with Edge AI.
Fully programmable
Algorithm agnostic
Host processor agnostic
RISC-V core to offload & run AI completely on-chip
Tyr 4
fp8: 1600 Tflops
fp16: 400 Tflops
Tyr 2
fp8: 800 Tflops
fp16: 200 Tflops
Tyr 4
fp8/int8: 50 Tflops
fp16/int16: 25 Tflops
fp32/int32: 12 Tflops
Tyr 2
fp8/int8: 25 Tflops
fp16/int16: 12 Tflops
fp32/int32: 6 Tflops
Close to theory efficiency
Fully programmable
Algorithm agnostic
Host processor agnostic
RISC-V cores to offload host
& run AI completely on-chip.
fp8: 3200 Tflops
fp16: 800 Tflops
fp8/int8: 100 Tflops
fp16/int16: 50 Tflops
fp32/int32: 25 Tflops
Close to theory efficiency