Semiconductor giant AMD, has announced that it has reached a definitive agreement to acquire Taalas, an AI chip startup founded and headquartered in Toronto, Canada, to strengthen its long-term AI roadmap with differentiated inference technology. This is significant in light of AI inference becoming one of the fastest-growing segments of the AI market and workloads becoming increasingly specialized.
Founded in 2023, Taalas’ technology aims to optimize inference dataflows, significantly reduce compute and memory bottlenecks associated with general-purpose architectures, and enable highly optimized AI inference capabilities.
Taalas’ technology will complement AMD’s full-stack AI platform, and the company’s expanding AI ecosystem. AMD plans to integrate the technology into its accelerator roadmap and develop system-level solutions with AMD Instinct GPUs.
“AMD is building a full-stack AI platform that gives customers the flexibility to deploy the right compute solutions for every AI workload,” said Vamsi Boppana, SVP, Artificial Intelligence Group, AMD said in a press release. “Taalas’ technology and world-class engineering team strengthen our AI portfolio by delivering differentiated inference performance and efficiency.”
“We founded Taalas to rethink AI inference from the ground up by building the hardware around the model,” said Ljubisa Bajic, co-founder and CEO of Taalas. “Our Canada-based team has combined deep technical expertise with a willingness to challenge conventional approaches. Joining AMD will give us the scale, engineering resources and global reach to accelerate our innovation.”
As AI moves into more real-time, high-volume applications, AMD and Taalas will help customers deploy inference workloads more efficiently across a growing range of applications. The acquisition is subject to customary closing conditions and regulatory approvals.
