Sign in

Compare repositories

This page shows the Star History and the facts of 2 to 5 repositories in the Repository Index, side by side. You choose the repositories. The page does not rank them.

Stars gained: From Oct 20, 2026 to Nov 5, 2026, each from zeroStars gainedFrom Oct 20, 2026 to Nov 5, 2026, each from zero05001KOct 20Nov 5, 2026eagle-hq/EAGLE-4syv-ai/HyperQwen
Stars: The star count at the end of each dayStarsThe star count at the end of each day01K2KAug 15Nov 5, 2026eagle-hq/EAGLE-4syv-ai/HyperQwen

Facts

Facteagle-hq/EAGLE-4

Official Inference Code of EAGLE-4

syv-ai/HyperQwen

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

Stars1,1552,567
Net stars, last 30 daysNot recorded+694
Largest star day+454 on Oct 20, 2026+128 on Aug 25, 2026
Milestone reached in the record1,000 on Oct 26, 20261,000 on Sep 1, 2026
Forks40325
LanguagePythonPython
LicenseOther licenseAPACHE-2.0
CreatedOct 20, 2026Aug 15, 2026
Last pushNov 1, 2026Nov 3, 2026
ArchivedNoNo
Health facts: Maintenance3 of 4 checks3 of 4 checks
Health facts: Releases3 of 3 checks0 of 3 checks (1 without data)
Health facts: Security practice1 of 1 check0 of 1 check
Health facts: Community files2 of 3 checks1 of 3 checks
Commits, last 13 weeks77654
Weeks with commits, last 523 of 5212 of 52
In the Repository Index sinceOct 23, 2026Oct 23, 2026

Topics that all of them have on the Repository Host: llm-inference, speculative-decoding, vllm. The facts come from the Repository Host and from the Star History that AwesomeRepos records. A shared topic does not mean that one repository can replace another. Each Health Facts row is one dimension alone. AwesomeRepos does not add them into one score. How each check is defined

Example: oven-sh/bun, denoland/deno, nodejs/node