sgl-project/sglang — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #2838 · UNIT ID 740303686

sgl-project/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00478

ENGAGEMENT0.96

FRESHNESS1.60

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

5% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

50.70

ACCEL

+0.52

RETENTION

47.6%

PEAK 2026-08-04 · FORK-RETENTION 82.0% · 1,521 STARS / WINDOW

Author Audience

AUDIENCE

10,567

FOLLOWERS

1,092

OWNER ★

41,913

Engagement Signals

FORKS

8,300

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 1,521 / 1,521 (DIVERSITY 1.00)

Why This Is A Finding

sgl-project/sglang собрал 1,521 звёзд за окно, тогда как у автора всего 1,092 подписчиков — эффективная аудитория ≈ 10,567. Это даёт surprise-индекс 0.00478 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 82.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 70% OF 9591 FINDINGS

#02guillaumemeyer/watermarks-remover[ PYTHON ]0.42 #09awesome-dsh-plugin/awesome-dsh-plugin[ PYTHON ]0.38 #11wang2122/sprix-sage-router[ PYTHON ]0.36 #16virgiliojr94/book-to-skill[ PYTHON ]0.31 #19ayghri/i-have-adhd[ PYTHON ]0.29

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9591 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.00ABOVE 70%

VELOCITY50.703.63+47.07ABOVE 96%

RETENTION47.6%24.8%+22.8 PPABOVE 88%

FORKS8,300120+8,180ABOVE 99%

SURPRISE0.000.01-0.00ABOVE 37%