TechPrufer
Get started
Google
Google logoGoogle · Feature trail

Memory-Efficient Serialization Libraries

2 posts · Apr 2015 – Aug 2024

What this trail covers

Google's development and promotion of memory-efficient serialization libraries, focusing on enabling high-performance data handling for applications. Early efforts introduced FlatBuffers, a serialization format designed for performance-critical applications, allowing direct access to data without parsing or unpacking. Subsequent developments have seen the release of FlatBuffers 1.1, which further enhances its capabilities and usability for developers. This has now been extended to include an improved API for C++ and Java, and support for C#.

All Google trails
  1. Streamlining LLM Inference at the Edge with TFLite- Google Developers BlogIntroduced an improved XNNPack weight cache provider for TensorFlow Lite. This provider utilizes memory-mapped files (mmap) to persist packed weights to disk, enabling them to be loaded across multiple TFLite interpreter instances and even across processes. This eliminates the overhead of repacking weights on each model load, significantly reducing startup latency and peak memory usage. It also allows for weight deduplication for models with shared subgraphs and simplifies the user-facing API by requiring only a cache file path.
  2. FlatBuffers 1.1: a memory-efficient serialization library- Google Developers BlogThis post announces FlatBuffers 1.1, a new version of the memory-efficient serialization library. It introduces an improved API for C++ and Java, and adds support for C#. This release aims to further enhance performance and usability for developers working with serialization.