Xiaopeng Wang's repositories
ai-town
A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.
AppFlowy
AppFlowy is an open-source alternative to Notion. You are in charge of your data and customizations. Built with Flutter and Rust.
aspire
An opinionated, cloud ready stack for building observable, production ready, distributed applications in .NET
Awesome-Black-Friday-Cyber-Monday
Awesome deals on Black Friday: Apps, SaaS, Books, Courses, etc.
Awesome-LLM-Eval
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, learderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向大型语言模型评测（例如ChatGPT、LLaMA、GLM、Baichuan等）.
Awesome-LLM-Inference
💻A small Collection for Awesome LLM Inference [Papers|Blogs|Docs] with codes, contains TensorRT-LLM, streaming-llm, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
ComfyUI
The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
DecryptPrompt
总结Prompt&LLM论文，开源数据&模型，AIGC应用
dspy
DSPy: The framework for programming—not prompting—foundation models
Efficient-LLMs-Survey
Efficient Large Language Models: A Survey
FlexFlow
A distributed deep learning framework.
generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
krita-ai-diffusion
Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.
litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
live
✯ 一个国内可直连的直播源分享项目 ✯ 🔕 永久免费 直连访问 完整开源 不含广告 完善的台标 直播源支持IPv4/IPv6双栈访问 🔕
llm-viz
3D Visualization of an GPT-style LLM
LLMs-from-scratch
Implementing a ChatGPT-like LLM from scratch, step by step
long-llms-learning
A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks
Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
MetaGPT
🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
MiniCPM
MiniCPM-2B: An end-side LLM outperforms Llama2-13B.
mlx
MLX: An array framework for Apple silicon
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
ragas
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
RWKV-LM
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, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
tools
useful tools for daily work
triton
Development repository for the Triton language and compiler
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities