Starred repositories
Multimodal OCR: Parse Anything from Documents
Multilingual Document Layout Parsing in a Single Vision-Language Model
modular service framework to move and transform network packets
High-performance Markdown and MDX processing for the JavaScript ecosystem
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
A high-performance and light-weight router for vLLM large scale deployment
Community maintained hardware plugin for vLLM on Apple Silicon
⚡ A fast Git hook manager written in Rust, designed as a drop-in alternative to pre-commit, reimagined.
The GitButler version control client, backed by Git, powered by Tauri/Rust/Svelte
A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
A binary distribution of the GNU RISC-V Embedded GCC toolchain
Fast and memory-efficient exact attention
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Sandbox your local AI agents so they can read/write only what they need
SGLang is a high-performance serving framework for large language models and multimodal models.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
An implementation of the ConnectRPC protocol for Rust
Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views
Runtime for executing procedural macros as WebAssembly
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
Opensource IDE For Exploring and Testing API's (lightweight alternative to Postman/Insomnia)
On-device, real-time multimodal AI with features similar to GPT-Live
Analyze Rust crates without touching compiler internals