Tether launches open-source QVAC SDK supporting localized AI and cross-platform deployment

ME News Report, April 9 (UTC+8), Stablecoin issuer Tether announced the launch of the QVAC SDK, a fully open-source, cross-platform software development kit designed to become a universal AI building module, supporting the operation, training, and evolution of artificial intelligence on any device and operating system. In terms of functionality, the SDK supports a variety of AI capabilities including large language models (LLMs), speech recognition, text generation, translation, OCR, and speech synthesis, all accessible through a unified API. Its underlying base is QVAC Fabric (originating from the llama.cpp branch) and it integrates local inference engines such as whisper.cpp, Parakeet, and Bergamot.

It is reported that the QVAC SDK adopts a “local-first” architecture, allowing developers to build and run AI applications directly on endpoint devices (such as smartphones, PCs, servers, etc.), enabling unified code deployment across iOS, Android, Windows, macOS, and Linux without the need for platform-specific adaptation or rewriting. In addition, the QVAC SDK also includes built-in peer-to-peer (P2P) capabilities based on the Holepunch technology stack, supporting decentralized model distribution, inference, and future distributed training, reducing reliance on centralized services.

Tether stated that it will continue to increase investment to expand the QVAC open-source ecosystem, covering cutting-edge fields such as robotics and brain-computer interfaces, and promote the shift of AI from cloud-based deployment to local deployment to meet requirements for privacy, low latency, and high reliability. (Source: ODAILY)