According to @hyperbolic_labs, UC Berkeley Sky Computing Lab researcher Sijun Tan built LLoCO, a technique that processes 128k context while using 30x fewer tokens. source: Hyperbolic Labs on X It delivers 7.62x faster inference in their reported case study. source: Hyperbolic Labs on X The project was powered by Hyperbolic Labs' NVIDIA H100 GPUs. source: Hyperbolic Labs on X

According to Paolo Ardoino, Tether Data has developed a fully private AI development kit that functions smoothly on iOS, emphasizing the flexibility for developers to execute the same code across various platforms. This includes compatibility with embedded devices, flagship smartphones, and clusters of H100 GPUs. The kit supports a translation application that can load weights from a peer-to-peer network, showcasing its versatility and potential for broad application in cryptocurrency and technology sectors.