ToolAI.io · GitHub 频道

GitHub 上的热门 AI 项目

一个基于事实的 LLM、智能体、MCP、RAG 和 AI 开发项目索引;每个条目均包含许可证、设置、下载、截图及相关资源。

公开仓库数据

项目索引

41 项目
推理、部署与运行时

OpenVINO

openvinotoolkit/openvino

用于在边缘到云环境中优化和部署 AI 推理的开源工具包。

★ 10.6K⑂ 3.3KC++
Apache-2.0Q98
推理、部署与运行时

Mooncake:以 KVCache 为中心的分布式 LLM 服务基础设施

kvcache-ai/mooncake

Mooncake 是一个面向大规模 LLM 推理和训练的 C++ 基础设施项目。它将预填充、解码和存储资源解耦,并提供高性能数据传输、分布式 KV 缓存存储及具备容错能力的专家并行通信。

★ 6.1K⑂ 1KC++
Apache-2.0Q98
推理、部署与运行时

llm-d:在 Kubernetes 上进行分布式 LLM 推理

llm-d/llm-d

llm-d 是一个开源服务栈,围绕 vLLM 和 SGLang 等模型服务器提供分布式编排、路由、缓存管理、自动扩缩容和批处理能力。它面向 Kubernetes 和现代硬件加速器上的大规模生产推理。

★ 4K⑂ 649Shell
Apache-2.0Q98
推理、部署与运行时

GPUStack

gpustack/gpustack

GPUStack 是一款开源 GPU 集群管理器,用于服务 AI 模型并按需提供可通过 SSH 访问的 GPU 实例。它可在本地部署、Kubernetes 和云环境中编排包括 vLLM、SGLang 和 TensorRT-LLM 在内的推理引擎。

★ 5.4K⑂ 604Python
Apache-2.0Q98
推理、部署与运行时

Model-Optimizer

NVIDIA/Model-Optimizer

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

★ 3.3K⑂ 513Python
Apache-2.0Q86
gpt-oss:Open-weight language model tooling 的截图
LLM 与基础模型

gpt-oss:Open-weight language model tooling

openai/gpt-oss

ToolAI 对 openai/gpt-oss 的客观项目介绍。gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

★ 20.3K⑂ 2.1KPython
Apache-2.0Q86
推理、部署与运行时

FastDeploy

PaddlePaddle/FastDeploy

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

★ 3.7K⑂ 755Python
Apache-2.0Q98
推理、部署与运行时

TensorRT

NVIDIA/TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

★ 13.2K⑂ 2.4KC++
Apache-2.0Q94
推理、部署与运行时

checkpoint-engine

MoonshotAI/checkpoint-engine

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

★ 982⑂ 100Python
MITQ83
计算机视觉

sam2

facebookresearch/sam2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

★ 19.6K⑂ 2.5KJupyter Notebook
Apache-2.0Q79
推理、部署与运行时

Paddle-Lite

PaddlePaddle/Paddle-Lite

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎)

★ 7.3K⑂ 1.6KC++
Apache-2.0Q91
机器人与边缘 AI

edgeai-for-beginners

microsoft/edgeai-for-beginners

This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimization, and the development of intelligent Edge AI agents.

★ 1.6K⑂ 362Jupyter Notebook
MITQ83

第 3 / 4 页 · 41 个项目

最近更新

cherry-studioCherryHQ/cherry-studio★ 51.5K siyuansiyuan-note/siyuan★ 46.2K career-opscareer-ops-hq/career-ops★ 70.2K tensorflowtensorflow/tensorflow★ 198.8K streamlitstreamlit/streamlit★ 45.7K pytorchpytorch/pytorch★ 102.8K

星标最多

ECCaffaan-m/ECC★ 248.8K Hermes Agentnousresearch/hermes-agent★ 227.1K tensorflowtensorflow/tensorflow★ 198.8K AutoGPTSignificant-Gravitas/AutoGPT★ 187.1K ollamaollama/ollama★ 180.2K markitdown:Document conversion and extractionmicrosoft/markitdown★ 174.9K