Project Icon

EasyDeL

Scalable Machine Learning Framework Using Jax/Flax for TPU and GPU

Product DescriptionEasyDeL is an open-source framework designed to enhance machine learning model training with a focus on JAX/Flax optimization for TPU and GPU. It supports a variety of model architectures and includes specialized trainers and efficient serving engines. Features include customizable sharding strategies, advanced quantization, and a flexible framework suitable for cutting-edge ML research. Regular updates provide access to the latest technologies, enabling scalable model training and experimentation with easy-to-use APIs.
Project Details