The LLM abstraction layer for modern AI agent applications.

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Kimi CLI is your next CLI agent.

PyTorch code and models for the DINOv2 self-supervised learning method.

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

红色警戒2源代码

Tongyi DeepResearch, the Leading Open-source DeepResearch Agent

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.

Godot Engine – Multi-platform 2D and 3D game engine

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Scalable toolkit for efficient model reinforcement

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Efficient Triton Kernels for LLM Training

Fast and memory-efficient exact attention

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

Inference and numerics for multi-hybrid AI model architectures

[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training

基于Python的开源量化交易平台开发框架