推理、部署与运行时
ray
ray-project/ray
为机器学习训练、调参和模型服务提供分布式计算运行时。
★ 43.7K⑂ 8KPython
ToolAI.io · GitHub 频道
GitHub 上的 AI 项目目录
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
多模态 AI
ComfyUI
Comfy-Org/ComfyUI
??????????????? AI ???????????????
★ 136.7K⑂ 16.3KPython
多模态 AI
TRELLIS.2：从图片生成带材质的 3D 资产
microsoft/TRELLIS.2
微软的 3D 生成项目，提供图片转三维、PBR 纹理生成与 GLB 导出，适合具备 GPU 环境的资产制作流程。
★ 11.2K⑂ 1.4KPython
推理、部署与运行时
NVIDIA Container Toolkit：让容器访问 NVIDIA GPU
NVIDIA/nvidia-container-toolkit
为 Docker 等容器运行时配置 GPU 访问，适合把模型推理、训练和 CUDA 工作负载部署到 NVIDIA GPU 服务器。
★ 4.6K⑂ 589Go
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
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
LLM 与基础模型
Qwen3：Open-weight multilingual language models
QwenLM/Qwen3
ToolAI 对 QwenLM/Qwen3 的客观项目介绍。Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud
★ 27.5K⑂ 2KPython
LLM 与基础模型
Qwen3-Coder：Code-focused language models
QwenLM/Qwen3-Coder
ToolAI 对 QwenLM/Qwen3-Coder 的客观项目介绍。Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team
★ 16.8K⑂ 1.2KPython
推理、部署与运行时
TensorRT-LLM：Optimized LLM inference
NVIDIA/TensorRT-LLM
ToolAI 对 NVIDIA/TensorRT-LLM 的客观项目介绍。TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way
★ 14.4K⑂ 2.7KC++
推理、部署与运行时
jan
janhq/jan
支持在个人电脑上运行模型的本地 AI 对话应用。
★ 44.3K⑂ 3KTypeScript
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
第 4 / 4 页 · 47 个项目