Github Trends®
8679 findingsmedian surprise 0.0046window 3 days
UNIT / TREND-MONITOR · REV 2.6
[ 3 days window ]
SOURCE: own snapshots
▲РЕПО НЕТ В ОКНЕ 90D. ПОКАЗАН FINDING ИЗ ОКНА 3D (3 days) — РАНГ #8420.
FINDING #8420 · UNIT ID 679366051
NVIDIA/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
[ PYTHON ][ ORG ][ VERIFIED ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.00000534
ENGAGEMENT1.00
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D
3.00
ACCEL
-0.50
RETENTION
62.5%
PEAK 2026-10-08 · FORK-RETENTION 71.4% · 9 STARS / WINDOW

Author Audience

AUDIENCE
561,823
FOLLOWERS
31,202
OWNER ★
437,900

Engagement Signals

FORKS
2,807
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 9 / 9 (DIVERSITY 1.00)

Why This Is A Finding

NVIDIA/TensorRT-LLM собрал 9 звёзд за окно, тогда как у автора всего 31,202 подписчиков — эффективная аудитория ≈ 561,823. Это даёт surprise-индекс 0.00000534 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 71.4% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 8679 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 3%
VELOCITY3.005.67-2.67ABOVE 10%
RETENTION62.5%42.4%+20.1 PPABOVE 76%
FORKS2,807334+2,473ABOVE 87%
SURPRISE0.000.00-0.00ABOVE 1%