Stars
A Rust Framework for Tracing, Automatic Differentiation, and Just-In-Time Compilation
TAPL is a modern compiler system's frontend framework designed to help users create their own strongly typed programming languages. It is designed to simplify the process of creating and extending …
lightweight, standalone C++ inference engine for Google's Gemma models.
A profiling and performance analysis tool for machine learning
An open-source AI agent that brings the power of Gemini directly into your terminal.
Qt based UI for visual and interactive composition and execution of MLIR compilation flows.
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
Custom Bindings for Enzyme Automatic Differentiation Tool and Interfacing with JAX.
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
Grandmaster-Level Chess Without Search
Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023
JAX - A curated list of resources https://github.com/google/jax
Repo for AI Compiler team. The intended purpose of this repo is for implementation of a PJRT device.
GoMLX: An Accelerated Machine Learning Framework For Go
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
Felafax is building AI infra for non-NVIDIA GPUs
Optimize Julia Functions With MLIR and XLA for High-Performance Execution on CPU, GPU, TPU and more.
Convert StableHLO models into Apple Core ML format
PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"
Experimental projects related to TensorRT
Support PyTorch model conversion with LiteRT.
A modern model graph visualizer and debugger