MARCH 6, 2026 / Cloud

What's new in TensorFlow 2.21

Google has officially launched LiteRT, the successor to TFLite, which offers significantly faster GPU and NPU acceleration alongside seamless support for PyTorch and JAX. The update also introduces lower-precision data type support for increased efficiency and a commitment to more frequent security and dependency updates across the TensorFlow ecosystem. This transition solidifies LiteRT as Google's primary high-performance framework for deploying GenAI and advanced on-device inference.

SEPT. 4, 2024 / AI Edge

TensorFlow Lite is now LiteRT

TensorFlow Lite, now named LiteRT, is still the same high-performance runtime for on-device AI, but with an expanded vision to support models authored in PyTorch, JAX, and Keras.

AUG. 13, 2024 / Mobile

Streamlining LLM Inference at the Edge with TFLite

XNNPack, the default TensorFlow Lite CPU inference engine, has been updated to improve performance and memory management, allow cross-process collaboration, and simplify the user-facing API.

JUNE 25, 2021 / AI

Developer updates from Coral

SEPT. 16, 2020 / AI

Doubling down on the edge with Coral's new accelerator

JULY 22, 2020 / AI

Summer updates from Coral

JAN. 2, 2020 / AI

New Coral products for 2020

DEC. 10, 2019 / AI

Object Detection and Tracking using MediaPipe

MAY 31, 2019

Coral updates: Project tutorials, a downloadable compiler, and a new distributor

APRIL 11, 2019 / AI

Updates from Coral: A new compiler and much more