eagle-hq/EAGLE-4
Official Inference Code of EAGLE-4
Updated 41 min ago
Maintain this repo? Add this badge to your README.
Growth
- Last 24 hours
- +279
- stars
- Last 7 days
- +642
- stars
- Last 30 days
- +642
- stars
- Total stars
- 642
- created 1 day ago
- Forks
- 4
Top 3 in LLM this week
- 1 xerj-org/xerj +8.3k stars this week
- 2 mmparko/dsh-purge +936 stars this week
- 3 eagle-hq/EAGLE-4 +642 stars this week
This repo: #3 of 509 this week, #2 of 154 today, #31 of 908 this month.
Also this week: #23 in Python
See all 509 LLM reposStar history
Total stars at the end of each week, from GitHub’s daily star counts.
Health signals
Too new to assessToo new to assess: the repository is less than 60 days old or has fewer than 10 commits. The signals below are shown for information only.
- Commit activity
- Commits this week (created this week) 18 commits on the default branch in 90 days
- Maintainers
- 1 commit author in 90 days Top author: 100% of the last 18 commits
- Issue responsiveness
- Too few issues to tell 0 issues opened by others in 90 days
- Pull requests
- None opened in 90 days
- Releases
- Last release: 1 day ago 1 release in the last 12 months
- Project hygiene
- License, CI and security policy
- OpenSSF Scorecard
- Not scanned Unknown, not counted against the project
Signals are computed automatically from public GitHub data. They are not an endorsement or a security audit. How health is computed
README
EAGLE-4
One Flexible Drafter for All Batch Sizes and Hardware
Figure 1(a) of the EAGLE-4 paper: Qwen3.8-27B on the SPEED-Bench qualitative split, 4× NVIDIA B300, one request, temperature 0. The numbers this release measured with EAGLE-4 are in the support matrix.