Early Exit: Noema Predictor (21M params, 98.3% accuracy, 3.8x speedup)
API: OpenAI-compatible server on port 8777
Paper
See rushd_agent_paper.pdf for full details.
Citation
bibtex
1@misc{yahya2025rushd,
2 title={Rushd-Agent}: An Efficient MoE-Based Agentic System with NCI-Driven Early Exit,
3 author={Yahya},
4 year={2025},
5 publisher={Hugging Face}
6}
