A MNIST model is defined and trained in Jax, then converted to TensorRT for inference.

distill large scale web page text

PySCF on IPU

[CVPR 2024] Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

XLA Launcher is a high-performance, lightweight C++ library designed to provide a simple interface for loading and executing computation graphs represented in the StableHLO format.

Event-based runtime for gang-scheduling multi-GPU operations across sharded arrays

PjRt plugin and Python APIs for MPMD workflows in Jax

JAX Foreign Function Interface experiments

SyntraLine++ is a compiler-based domain-specific language (DSL) for defining, validating, and executing machine learning pipelines with PyTorch and JAX backends with C++ architectural foundations.

PlannerSandbox is a ROS 2–based Python, C++ repository providing clean, example-driven implementations of sampling-based motion planning methods, including MPPI variants, spline-based planning, and multi-agent scenarios.

Digital Audio Workstation with Python; VST instruments/effects, parameter automation, FAUST, JAX, Warp Markers, and JUCE processors

Wraps GPUMD simulation data as DLPack tensors for PySAGES/JAX integration

Functional programming language for signal processing and sound synthesis

A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.

JAX interface for XSPEC spectral models.

True randomness for AI and machine learning. Non-recursive, stateless, cryptographically secure random number generator.

A retargetable MLIR-based machine learning compiler and runtime toolkit.