txsun1997/awesome-early-exiting

A curated list of Early Exiting papers, benchmarks, and misc.

39
/ 100
Emerging

This resource helps machine learning practitioners find research papers and benchmarks related to 'Early Exiting' techniques, primarily in Natural Language Processing. It provides a curated list of research that shows how to make large language models predict results faster without losing accuracy. Data scientists or AI researchers focused on model optimization would use this to stay updated on efficiency improvements for deep learning models.

119 stars. No commits in the last 6 months.

Use this if you are working with large language models and need to find methods to significantly speed up their inference time for real-time applications or resource-constrained environments.

Not ideal if you are looking for ready-to-use code implementations or a general overview of machine learning optimization techniques beyond early exiting.

Natural Language Processing Deep Learning Optimization Model Efficiency AI Research Language Model Inference
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

119

Forks

12

Language

License

MIT

Last pushed

Oct 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/txsun1997/awesome-early-exiting"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.