Turiyam AI has successfully deployed its inference engine on indigenous Rudra 1 and Rudra 2 servers at Centre for Development of Advanced Computing in Pune, marking a significant milestone in building a fully integrated Indian AI stack.

The deployment combines a locally developed large language model, inference engine, and server infrastructure within a high-performance computing environment. As part of validation, a Hindi-focused LLM covering 37 dialects ran successfully, demonstrating the capability of domestically engineered systems to handle advanced AI workloads.

Commenting on the achievement, Sanchayan Sinha noted that the milestone reinforces India’s ability to run sophisticated AI systems without relying on external infrastructure. Magesh E. added that the validation reflects the growing maturity of India’s innovation ecosystem.

The development aligns with India’s accelerating AI infrastructure push, supported by collaborations involving BharatGen Technology Foundation and IIT Bombay.