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
评估、可观测性与安全
garak：LLM vulnerability scanning
NVIDIA/garak
ToolAI 对 NVIDIA/garak 的客观项目介绍。the LLM vulnerability scanner
★ 8.9K⑂ 1.2KPython
LLM 与基础模型
MiniMax-M2
MiniMax-AI/MiniMax-M2
MiniMax-M2, a model built for Max coding & agentic workflows.
★ 2.6K⑂ 215—
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
评估、可观测性与安全
evals：Model evaluation framework
openai/evals
ToolAI 对 openai/evals 的客观项目介绍。Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks
★ 19.2K⑂ 3.1KPython
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++
LLM 与基础模型
PaddleFormers
PaddlePaddle/PaddleFormers
PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.
★ 13K⑂ 2.2KPython
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
第 10 / 10 页 · 118 个项目