ANEE
Apache-2.0Pythonv0.3
A dynamic inference wrapper for Transformer language models that enables per-token layer skipping to reduce computational FLOPs.
2 stars0 forks0 contributors
Overview
ANEE is an experimental dynamic inference wrapper for pretrained Transformer language models (currently GPT-2). Instead of always running all layers, ANEE exposes an energy_budget and performs early exit inside the model’s forward pass.
Related Projects
Community-curated · Updated weekly · 100% open source
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
