这是一个基于 Next.js 构建的多语言 AI 模型评估平台，支持多模型对比和实时流式响应。A multilingual AI model evaluation platform built with Next.js, allowing users to compare responses from multiple models and receive a final judgment.

SimpleX - the first messaging network operating without user identifiers of any kind - 100% private by design! iOS, Android and desktop apps 📱!

VideoSys: An easy and efficient system for video generation

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

FDU CS自学指南

🐱给小白的Shadowsocks翻墙教程-Easy-to-follow tutorials for beginners on using Shadowsocks to bypass internet restrictions.

A native PyTorch Library for large model training

Efficient GPU kernels for block-sparse matrix multiplication and convolution

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

Next Generation of ShadowsocksX

compiler learning resources collect.

Mamba SSM architecture

Collection of papers on state-space models

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Converts LaTeX documents to HTML

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

[ECCV24] Attention Regulation on T2I Diffusion Models

一款照片水印添加工具

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Latte: Latent Diffusion Transformer for Video Generation.

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

Open-Sora: Democratizing Efficient Video Production for All