Official implementation of Half-Quadratic Quantization (HQQ)

Stable Diffusion web UI

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

VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.

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

A Native-PyTorch Library for LLM Fine-tuning

My blog

QLoRA: Efficient Finetuning of Quantized LLMs

A framework for few-shot evaluation of language models.

Accessible large language models via k-bit quantization for PyTorch.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

LLM inference in C/C++

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Stride visualizations

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

🔥🔥🔥 Web-based linux server management control panel. / 现代化、开源的 Linux 服务器运维管理面板。

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Clash Nyanpasu～(∠・ω< )⌒☆​

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Capstone disassembly/disassembler framework for ARM, ARM64 (ARMv8), Alpha, BPF, Ethereum VM, HPPA, LoongArch, M68K, M680X, Mips, MOS65XX, PPC, RISC-V(rv32G/rv64G), SH, Sparc, SystemZ, TMS320C64X, T…

Towards Large-Scale Emulation of IoT Firmware for Dynamic Analysis

A client implementation for ChatGPT and Bing AI. Available as a Node.js module, REST API server, and CLI app.

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

Reverse engineered ChatGPT API

Making large AI models cheaper, faster and more accessible