Eric Buehler

Fast, flexible LLM inference

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

A Python Interpreter written in Rust

🍻 Default formulae for the missing package manager for macOS (or Linux)

A high-throughput and memory-efficient inference and serving engine for LLMs

MiniJinja is a powerful but minimal dependency template engine for Rust compatible with Jinja/Jinja2

The Python programming language

LlamaIndex is a data framework for your LLM applications

MLX: An array framework for Apple silicon

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

CLI utility to inspect and explore .safetensors and .gguf files

DORA (Dataflow-Oriented Robotic Application) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dataflow capabilities. Applications are modeled as directed graphs, also referred to as pipelines.

Safe rust wrapper around CUDA toolkit

Blazingly fast inference of diffusion models.

Falcon is a powerful, interpreted programming language.

MXFP4-compatible 4-bit floating point types and block formats for Rust.

X-LoRA: Mixture of LoRA Experts

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

dLLM: Simple Diffusion Language Modeling

Edge(u)cation: Cutting-edge multimodal LLMs on the edge with mistral.rs, using F8Q8

8-bit floating point types for Rust

An autonomous robot, powered by AI.

fused MoE kernel in Candle backend

a complex numbers, 2d/3d graphing, arbitrary precision, vector, cli calculator with real-time output

A high efficiency binary format for sequencing data

Rust bindings for the C++ api of PyTorch.

Fork of std::sync::Arc with lots of utilities useful for FFI

A faster Arc.

Rust implementation of VibeVoice text-to-speech with voice cloning and multi-speaker synthesis.

Rust implementation of the Mistral Tekken tokenizer