A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

OpenAPI Generator allows generation of API client libraries (SDK generation), server stubs, documentation and configuration automatically given an OpenAPI Spec (v2, v3)

LLM inference in C/C++

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

A Datacenter Scale Distributed Inference Serving Framework

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Minimalist ML framework for Rust

Rust multiprovider generative AI client (Ollama, OpenAi, Anthropic, Gemini, DeepSeek, xAI/Grok, Groq,Cohere, ...)

This repository contains the Hugging Face Agents Course.

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Development repository for the Triton language and compiler

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Modular, contributor-friendly and blazing-fast implementation of the Ethereum protocol, in Rust

Web-Scale Blockchain for fast, secure, scalable, decentralized apps and marketplaces.

Rust implementation of the Ethereum Virtual Machine.

🦜🔗 Build context-aware reasoning applications

the AI-native open-source embedding database

Deep learning at the speed of light.

Open source platform for the machine learning lifecycle

Apache DataFusion Comet Spark Accelerator

Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

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

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Mirror of Apache Spark

A high-performance observability data pipeline.

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Ergonomic and modular web framework built with Tokio, Tower, and Hyper

Glommio is a thread-per-core crate that makes writing highly parallel asynchronous applications in a thread-per-core architecture easier for rustaceans.