Make LLM Efficient Again!
The BJTU Edge Computing & Edge Intelligence Group is pioneering the integration of large language models with edge devices. Our current focus areas include:
✓ Token Optimization
✓ Distributed Inference
✓ Speculative Decoding
✓ LLM Routing
Llama2 on Jetson Orin Nano
DeepSeek-R1 on Windows Laptop
Gemma on Android Phone
© 2026 Weiwei Fang. All Rights Reserved.
内容未经允许不得复制、镜像。