ToolAI.io · Kênh GitHub
Theo dõi các kho lưu trữ AI mã nguồn mở đang hoạt động trong các chủ đề LLM, tác nhân, MCP, RAG và lập trình, kèm số sao và thông tin dự án đã xác minh.
Dữ liệu kho lưu trữ công khai
huggingface/transformers
A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal domains, supporting both inference and training.
opencsgs/csghub
CSGHub is an open-source, on-premise platform for managing the full lifecycle of Large Language Model assets, including models, datasets, spaces, and code, offering functionality comparable to a private Hugging Face.
lemonade-sdk/lemonade
Lemonade is an open-source local AI server that enables users to run optimized Large Language Models (LLMs), speech, and image generation models directly on their own GPUs and NPUs, providing a free and private alternative to cloud APIs.
openvinotoolkit/openvino
Open-source toolkit for optimizing and deploying AI inference across edge-to-cloud environments.
kvcache-ai/mooncake
Mooncake is a C++ infrastructure project for large-scale LLM inference and training. It separates prefill, decode, and storage resources while providing high-performance transfer, distributed KV-cache storage, and fault-tolerant expert-parallel communication.
llm-d/llm-d
llm-d is an open-source serving stack that adds distributed orchestration, routing, cache management, autoscaling, and batch processing around model servers such as vLLM and SGLang. It targets high-scale production inference on Kubernetes and modern hardware accelerators.
gpustack/gpustack
GPUStack is an open-source GPU cluster manager for serving AI models and provisioning on-demand, SSH-accessible GPU instances. It orchestrates inference engines including vLLM, SGLang, and TensorRT-LLM across on-premises, Kubernetes, and cloud environments.
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.
NVIDIA/nvidia-container-toolkit
Configures NVIDIA GPU access for container runtimes such as Docker, supporting containerized inference, training and CUDA workloads.
openai/gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
PaddlePaddle/FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
microsoft/TRELLIS.2
Microsoft’s 3D generation project with image-to-3D inference, PBR texturing and GLB export for GPU-equipped asset workflows.
Trang 3 / 4 · 47 dự án
