LayerSkip
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
Implement early exit inference and self-speculative decoding techniques in language models to improve performance.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeCode for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
LayerSkip has 371 stars on GitHub. It has been forked 45 times. LayerSkip is written mainly in Python. It has been in active development since 2024. Its main topics are early-exit, layer-drop, llm, optimization.
What is LayerSkip?
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
Is LayerSkip open source?
LayerSkip is an open-source project.
Is LayerSkip free?
Yes. LayerSkip is free and open source — you can use, modify and self-host it.
What language is LayerSkip written in?
LayerSkip is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/facebookresearch-layerskip.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.