FINDING #9114 · UNIT ID 790916393
NVIDIA/Model-Optimizer
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
1% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
6.29
ACCEL
+0.86
RETENTION
0.0%
PEAK 2026-08-28 · FORK-RETENTION 0.0% · 44 STARS / WINDOW
Author Audience
AUDIENCE
524,769
FOLLOWERS
29,451
OWNER ★
414,853
Engagement Signals
FORKS
557
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 44 / 44 (DIVERSITY 1.00)
Why This Is A Finding
NVIDIA/Model-Optimizer собрал 44 звёзд за окно, тогда как у автора всего 29,451 подписчиков — эффективная аудитория ≈ 524,769. Это даёт surprise-индекс 0.000012 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 7% OF 9760 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9760 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 7%
VELOCITY6.293.71+2.57ABOVE 67%
RETENTION0.0%38.0%-38.0 PPABOVE 0%
FORKS55786+471ABOVE 88%
SURPRISE0.000.01-0.01ABOVE 1%