Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Open-Sora: Democratizing Efficient Video Production for All

Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer

深度学习经典、新论文逐段精读

Code behind Arxiv Papers

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Open source code for AlphaFold.

清华大学计算机系考研攻略 Guidance for postgraduate entrance examination in Department of Computer Science and Technology, Tsinghua University

A PyTorch Library for Accelerating 3D Deep Learning Research

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

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

This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation is overly complex and lacks extensibility. Let's join the f…

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

A simple and efficient Mamba implementation in pure PyTorch and MLX.

Visual Studio Code

Generative Models by Stability AI

MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

Mamba SSM architecture

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

Scaling RWKV-Like Architectures for Diffusion Models

Ongoing research training transformer models at scale

Remote vanilla PDB (over TCP sockets).

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

Making large AI models cheaper, faster and more accessible