Stars
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
from vibe coding to agentic engineering - practice makes claude perfect
Video Content Customization Using First Frame
Magnificent app which corrects your previous console command.
An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
Wan: Open and Advanced Large-Scale Video Generative Models
DeepGEMM: clean and efficient BLAS kernel library on GPU
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Gemma open-weight LLM library, from Google DeepMind
Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
Instant voice cloning by MIT and MyShell. Audio foundation model.
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
Transformer related optimization, including BERT, GPT
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
ModelScope: bring the notion of Model-as-a-Service to life.
Universal LLM Deployment Engine with ML Compilation
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
Making large AI models cheaper, faster and more accessible
Official repo for consistency models.
Machine learning resources,including algorithm, paper, dataset, example and so on.