MuLabPKU/TransArch

TransArch

✅ Recently maintained

Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss

517Stars

35Forks

+47-day stars

Python · License unverified · Last push 2026-10-23

Star history

2025-09-292026-11-02

View historical data

git clone https://github.com/MuLabPKU/TransArch.git

Related domains do not imply feature parity. Review official documentation and licenses.

Run DeepSeek, Qwen, Gemma and other LLMs locally with one command, plus model management and an API.

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Finetune Llama, Mistral and other LLMs 2-5x faster with 80% less memory.