llama.cpp — a leading open-source project in the AI/LLM ecosystem.

vLLM — a leading open-source project in the AI/LLM ecosystem.

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Find secrets with Gitleaks 🔑

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

✍🏻 Source Code Deep Dives, System Design & Engineering Blogs | Halfrost-Field 冰霜之地：源码解析、系统设计与工程实践笔记

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

Official inference library for Mistral models

High-speed Large Language Model Serving for Local Deployment

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

A Datacenter Scale Distributed Inference Serving Framework

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Open-source implementation of AlphaEvolve

Plano is an AI-native proxy server and data plane for agentic apps - centralizing orchestration, safety, observability, and smart LLM routing so you can deliver agents faster.

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

FlashInfer: Kernel Library for LLM Serving

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

Performance-optimized AI inference on your GPUs. Unlock superior throughput by selecting and tuning engines like vLLM or SGLang.

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

RuVector is a High Performance, Real-Time, Self-Learning, Vector Graph Neural Network, and Database built in Rust.

RuVector is a High Performance, Real-Time, Self-Learning, Vector Graph Neural Network, and Database built in Rust.

Optimizing inference proxy for LLMs

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

A collection of scientific methods, processes, algorithms, and systems to build stories & models.

Sparsity-aware deep learning inference runtime for CPUs

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents.

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)

A highly optimized LLM inference acceleration engine for Llama and its variants.

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/Linux with full GPU capability

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Rust + CUDA inference engine for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. Serves safetensors and GGUF over an OpenAI-compatible API, with per-device tuned defaults and speculative decode gated byte-identical to plain decode. Hosted instance: inference.tiyuvta.ai