Built in Python, EAGLE is an open-source LLM inference tool maintained by SafeAILab. The repository has collected 2.6k stars and 297 forks; the latest push was in February 2026. Docs and downloads are linked from arxiv.org.
“Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).”
— SafeAILab, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 2,555 |
| Forks | 297 |
| Language | Python |
| Last updated | |
| Owner | SafeAILab |
| Website | arxiv.org/pdf/2503.01840 |
| Repository | SafeAILab/EAGLE |
Tags
large-language-modelsllm-inferencespeculative-decoding
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.