Run Local LLMs on Any Device. Open-source
MII makes low-latency and high-throughput inference possible
A set of Docker images for training and serving models in TensorFlow
Bring the notion of Model-as-a-Service to life
GPU environment management and cluster orchestration
PyTorch extensions for fast R&D prototyping and Kaggle farming
Powering Amazon custom machine learning chips
The unofficial python package that returns response of Google Bard