Furiosa AI's 'RNGD (Renegade)' will support the implementation of LG's large-scale language model (LLM) 'EXAONE' infrastructure, and will begin to attack the AI ecosystem of LG affiliates and partners in earnest. Expectations are high that it will emerge as an alternative to GPU in the future.

AI semiconductor company Furiosa AI (CEO Baek Jun-ho) announced on the 22nd that its second-generation AI inference accelerator 'RNGD (Renegade)' has been fully introduced to LG's large-scale language model (LLM) 'EXAONE'.

Based on this collaboration, the two companies will soon launch an enterprise ExaOne solution based on Renegade.

This collaboration is seen as a strategic turning point in improving AI data center power efficiency and providing an alternative to GPUs.

In approximately eight months of pilot testing, Renegade met all of LG AI Research’s high-performance requirements while delivering a 2.25x performance-per-watt improvement over conventional GPUs.

By overcoming the limitations of GPUs, which were pointed out as excessive power consumption, we have achieved both reduction in total cost of ownership (TCO) and maximization of power efficiency in AI data centers.

The solution can be applied across all areas of AI infrastructure, including top-of-rack switches, power supply units (PSUs), battery backup systems, and DC-DC networking.

Furiosa AI cited significant improvements in power density and stability through optimization of the 48V intermediate bus converter and power module design as innovation points.

In particular, as major technology-leading countries focus on securing AI sovereignty, the introduction of Renegade has high strategic value in that it demonstrates the possibility of self-reliance in AI infrastructure based on domestic NPU.

It is attracting attention as an important model that can reduce GPU dependency and operate AI workloads with its own solution.

This case is the first monumental case in Korea where hardware other than GPUs has been introduced to a large-scale enterprise LLM inference environment.

Through this, Furiosa AI has proven its technological prowess and reliability.Zeng plans to fully attack the market for corporate AI solutions targeting Fortune Global 500 companies.

“Renegade has excellent absolute performance and excellent infrastructure TCO reduction effect,” said Jeon Ki-jeong, head of LG AI Research Product Unit. “The fast and easy model support process is also a major strength.”

FuriosaAI CEO Baek Jun-ho said, “ExaOne is emerging as a national foundation model for Korea,” and added, “We will contribute to building a high-performance national AI infrastructure through continuous cooperation.” He continued, “This collaboration will become a model for companies around the world to proactively design and operate AI infrastructure.”

FuriosaAI is preparing to support ExaOne 4.0, the successor to ExaOne 3.5, and will soon launch an on-premise, turnkey enterprise ‘ExaOne AI Solution’ based on Renegade.

This is expected to accelerate the spread of domestic NPUs that replace GPUs and focus on power efficiency across the AI ecosystem.