Stars
An transformer based LLM. Written completely in Rust
Simple, safe way to store and distribute tensors
Create a good-looking DMG for your macOS app in seconds
💫 Industrial-strength Natural Language Processing (NLP) in Python
On-device AI across mobile, embedded and edge for PyTorch
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Open source annotation tool for machine learning practitioners.
C++ Insights - See your source code with the eyes of a compiler
JVector: the most advanced embedded vector search engine
Fast. Easy. Done. Processing Excels without worrying about large files causing OOM.
Tools and samples for understanding Apple's Metal shading language and its LLVM Bitcode shader files
A GPU accelerated image and video processing framework built on Metal.
macOS and Linux VMs on Apple Silicon to use in CI and other automations
MoltenVK is a Vulkan Portability implementation. It layers a subset of the high-performance, industry-standard Vulkan graphics and compute API over Apple's Metal graphics framework, enabling Vulkan…
Work with remote images registries - retrieving information, images, signing content
Run macOS VM in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X Security Research! Docker mac Containers.
Ready-to-run Docker images containing Jupyter applications
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.