foreverpiano

OSD

attention-gym

Helpful tools and examples for working with flex-attention

PKU-Auto-Reservation

华清大学自动预约入校

zotero-style

Ethereal Style for Zotero

cold-compress

Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.

CogVideo

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

SEED-Story

SEED-Story: Multimodal Long Story Generation with Large Language Model

anole

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

flux

Official inference repo for FLUX.1 models

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

shell_gpt

A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently.

ktransformers

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

cook

🍲 好的，今天我们来做菜！OK, Let's Cook!

patch_conv

Patch convolution to avoid large GPU memory usage of Conv2D

retrieval-scaling

Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

DiT-MoE

Scaling Diffusion Transformers with Mixture of Experts

ngram

The n-gram Language Model

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

ShareGPT4Video

An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Awesome-Efficient-Diffusion-Models

Paper survey of efficient computation for large scale models.

VBench

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

DeepCache

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

onediff

OneDiff: An out-of-the-box acceleration library for diffusion models.

stable-fast

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Latte

Latte: Latent Diffusion Transformer for Video Generation.