从 65,730 个高星开源项目里，
找到你要的下一个。

FreeVideo 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration pa…

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

agibot_x1_infer 是用 C++ 编写的 AI 工具，用于大模型与智能体应用开发。

The inference module for AgiBot X1.

NNPACK 是用 C 编写的 AI 工具，用于人工智能方向的建模与推理。

Acceleration package for neural networks on multi-core CPUs

transformer-deploy 是用 Python 编写的学习资料，用于系统学习与查阅，主打可伸缩、适合生产环境。

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

llmgateway 是用 TypeScript 编写的 AI 工具，用于大模型与智能体应用开发。

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

StartLux-Decision 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM,…

delta 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/

xllm 是用 C++ 编写的 AI 工具，用于大模型与智能体应用开发，主打高性能。

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

nvidia_gpu_exporter 是用 Go 编写的 AI 工具，用于大模型与智能体应用开发。

Nvidia GPU exporter for prometheus using nvidia-smi binary OR using NVML

TurboTransformers 是用 C++ 编写的 AI 工具，用于人工智能方向的建模与推理，主打速度快、易用。

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

sglang-omni 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发，主打高性能。

SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.

rtp-llm 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发，主打高性能。

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

budgetml 是用 Python 编写的学习资料，用于系统学习与查阅。

Deploy a ML inference service on a budget in less than 10 lines of code.

EmbedAnything 是用 Rust 编写的 AI 工具，用于人工智能方向的建模与推理，主打高性能、内存安全、适合生产环境。

Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

awesome-ml-demos-with-ios 是用 Python 编写的资源清单，按主题汇总同类优质资源。

The challenge projects for Inferencing machine learning models on iOS

BERT-NER 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

Pytorch-Named-Entity-Recognition-with-BERT

CausalDiscoveryToolbox 是用 Python 编写的学习资料，用于系统学习与查阅。

Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.

kvpress 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发，主打易用。

LLM KV cache compression made easy

kubetorch 是用 Python 编写的运维工具，用于部署、编排与监控。

Distribute and run AI workloads on Kubernetes magically in Python, like PyTorch for ML infra.

ai-hub-models 是用 Python 编写的学习资料，用于系统学习与查阅。

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to …

cpu-performance-engineering 是用 Python 编写的资源清单，按主题汇总同类优质资源。

A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for ev…

tiny-vllm 是用 C++ 编写的 AI 工具，用于大模型与智能体应用开发，主打高性能。

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

agentmesh 是用 Go 编写的 AI 工具，用于大模型与智能体应用开发。

Agent Mesh