Google open sources XLA Serving Engine to run ML models without Python

The C++ runtime already serves over 6 million queries per second inside Google, and now anyone can use it Google has open-sourced the XLA Serving Engine, or XSE, a C++ runtime that serves compiled machine learning models with no Python involved. Google announced the release on November 5, 2026, under the Apache 2.0 license. The company says the engine is already battle-tested at scale, handling over 6 million queries per second internally across products including YouTube Shorts and Google Ads. XSE tackles that split directly. Developers can train deep learning models in JAX or PyTorch, then export them into a standalone C++ environment. Once exported, the model runs without the Python interpreter tagging along.

BeCrypto News shows a short excerpt and links to the publisher. The full report belongs to Crypto Briefing.