AMD acquires AI chip startup Taalas to further support inference workloads

AMD has acquired Canadian AI chip startup Taalas to integrate its technology into AMD Instinct GPUs for more efficient inference workloads. Financial terms were not disclosed. Taalas, founded in August 2023 by Ljubisa Bajic, raised $169 million in February 2026 and unveiled its HC1 processor optimized for Llama 3.1 8B, claiming superior performance and one-tenth the power of Nvidia's H200 and B200.

AMD has acquired Canadian AI chip startup Taalas, saying it plans to integrate Taalas’ technology to “develop system-level solutions with AMD Instinct GPUs.” In a statement, AMD said the acquisition will allow the company to help customers deploy inference workloads more efficiently across a growing range of applications. The financial terms of the deal were not disclosed, and the companies did not provide a timeline for when the deal is expected to close. Taalas was founded in August 2023 by Ljubisa Bajic, a former architect at both AMD and Nvidia and Tenstorrent https://www.datacenterdynamics.com/en/news/ai-and-risc-v-chip-company-tenstorrent-raises-100m-from-hyundai-kia-and-samsung/ co-founder, alongside engineers Drago Ignjatovic and Lejla Bajic. In October 2022, Bajic job-swapped https://www.datacenterdynamics.com/en/news/jim-keller-becomes-ceo-of-ai-chip-company-tenstorrent/ with Tenstorrent CTO Jim Keller, before stepping down from the company entirely in March the following year. In February 2026, the startup raised https://www.datacenterdynamics.com/en/news/ai-chip-startup-taalas-raises-169m-unveils-hc1-processor-optimized-for-llama-31-8b/ $169 million to support the development of chips that have been optimized for specific AI models. At the same time, Taalas also unveiled its first chip, the HC1 Technology Demonstrator, which has been optimized to run the open-source Llama 3.1 8B language model. Fabricated by Taiwan Semiconductor Manufacturing Company TSMC TSMC using its 6nm process node, Taalas claims its chips can generate more tokens per second per user than Nvidia’s H200 and B200 offerings, as well as hardware from Groq, SambaNova, and Cerebras, whilst using one tenth of the power. “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 of the Artificial Intelligence Group at AMD. "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 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.” The acquisition follows AMD's financials for the second quarter https://www.datacenterdynamics.com/en/news/amd-posts-q2-26-revenue-of-115bn-with-data-center-revenue-up-107-for-the-quarter/ , which generated total revenue of $11.5 billion, up 50% year-over-year YoY and 13% quarter-over-quarter QoQ .