zineos

Agent4Rec

The implementation of paper "On Generative Agents in Recommendation"

calculon

Chat-Haruhi-Suzumiya

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

cpp_interview

c++后台服务器开发面经或八股总结！(有深度有广度，和仅有概念的总结文章不同！)

Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

DistServe

Disaggregated serving system for Large Language Models (LLMs).

DocsGPT

GPT-powered chat for documentation, chat with your documents

FunClip

Open-source, accurate and easy-to-use video clipping tool, LLM based AI clipping intergrated || 开源、精准、方便的视频切片工具，集成了大语言模型AI智能剪辑功能

GPTSwarm

🐝 GPTSwarm: LLM agents as (Optimizable) Graphs

graph-of-thoughts

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

InferLLM

a lightweight LLM model inference framework

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

LazyLLM

Easyest and lazyest way for building multi-agent LLMs applications.

lectures

Material for cuda-mode lectures

llm-on-ray

Pretrain, finetune and serve LLMs on Intel platforms with Ray

llm_interview_note

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

mllm

Fast Multimodal LLM on Mobile Devices

mpv-upscale-2x_animejanai

Real-time anime upscaling to 4k in mpv with Real-ESRGAN compact models

PromptIR

PromptIR: Prompting for All-in-One Blind Image Restoration [NeurIPS 2023]

ProPainter

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

QAnything

Question and Answer based on Anything.

qllm-eval

Code Repository of Evaluating Quantized Large Language Models

rwkv

RWKV model implementation

shezhangbujianle

借助世界上最大的单体中文NLP大模型，我们做出了一个可以跟人类玩“剧本杀”的AI……

swiftLLM

A tiny yet powerful LLM inference system tailored for researching purpose

tiny-flash-attention

flash attention tutorial written in python, triton, cuda, cutlass

tiny-universe

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

trt_final

video-subtitle-remover

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

vidur

A large-scale simulation framework for LLM inference