Lists (1)
Stars
This repository organizes the Imagnet1k dataset into 10 coarse classes, where each class consists of semantically similar image categories.
VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework
An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps
The official implementation of Recurrent Diffusion for Large-Scale Parameter Generation.
Enhance-A-Video: Better Generated Video for Free
A curated list of recent efficient video generation methods.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
oahzxl / Open-Sora
Forked from hpcaitech/Open-SoraOpen-Sora: Democratizing Efficient Video Production for All
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"
[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters
VideoSys: An easy and efficient system for video generation
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…
how to optimize some algorithm in cuda.
The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams
A collection of memory efficient attention operators implemented in the Triton language.
Automated Parallelization System and Infrastructure for Multiple Ecosystems
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
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.
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.
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)