
Google Cloud has open-sourced TPU Sync, a native C++ library that moves KV cache blocks and model weights between TPU HBM, host DRAM, shared storage, and the data center network.
By Daniel Dominguez
Google Cloud has open-sourced TPU Sync, a native C++ library that moves KV cache blocks and model weights between TPU HBM, host DRAM, shared storage, and the data center network.
By Daniel Dominguez