torch

VoxNovel: generate audiobooks giving each character a different voice actor.

Persist and reuse KV Cache to speedup your LLM.

ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60

Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).

Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

Deep Learning Deployment Framework: Supports tf/torch/trt/trtllm/vllm and other NN frameworks. Support dynamic batching, and streaming modes. It is dual-language compatible with Python and C++, offering scalability, extensibility, and high performance. It helps users quickly deploy models and provide services through HTTP/RPC interfaces.

deep learning

DocMind AI is a powerful, open-source Streamlit application leveraging LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama.cpp, or vLLM for advanced document analysis. Analyze, summarize, and extract insights from a wide array of file formats, securely and privately, all offline.

Universal Python SDK to run AI workloads on Kubernetes

Few-shot Named Entity Recognition

This repository guides you through the process of building a GPT-style Large Language Model (LLM) from scratch using PyTorch. The structure and approach are inspired by the book Build a Large Language Model (From Scratch) by Sebastian Raschka.

A Blender add-on for generating free textures using the Stable Diffusion AI text to image model.

easy-bert是一个中文NLP工具，提供诸多bert变体调用和调参方法，极速上手；清晰的设计和代码注释，也很适合学习

Telegram bot with voice message recognition and generation. Speech to Text and Text to Speech

TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder

Fully automatic asynchronous AI operated Twitter bot using Large Language Models through OpenAI and Hugging Face to schedule and generate contextual content.

Fastest Diffusion backend, WebUI, server. Pushing implementation and discovery of optimizations techniques 🚀

ModelSoups for Tensorflow2 and Torch

A clean, single-file PyTorch implementation of Attention Residuals (Kimi Team, MoonshotAI, 2026), integrated with Grouped Query Attention (GQA), SwiGLU feed-forward networks, and Rotary Position Embeddings (RoPE).

🚀 A simple, modern, full-stack toolkit for Python 🐍