Showing 1-12 of 12 projects
High-throughput LLM inference engine for developers
A library of deep learning models and datasets to make deep learning more accessible and accelerate ML research.
Easily run, manage, and scale AI workloads on any infrastructure using a unified platform.
Reference models and tools for Cloud TPUs, a hardware accelerator for machine learning.
CodeGen is an open-source family of models for program synthesis, competitive with OpenAI Codex.
A JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU for speech-to-text tasks.
A flexible AutoML framework with learning guarantees for building high-performance AI models.
Enables PyTorch, a popular machine learning library, to run on XLA devices like Google TPUs.
A library that provides insights into the internals of Apple's Neural Engine for iOS developers.
GPT-2 multi-language pre-trained models, including a 1.5B parameter Chinese model, for text generation and NLP tasks.
A large-scale LLM inference engine built in C++ with support for various AI hardware accelerators.
A minimal tensor processing unit (TPU) for AI and machine learning workloads, inspired by Google's TPU V2 and V1.
Get weekly updates on trending AI coding tools and projects.