amitshekhariitbhu/llm-inference-engineering — GitHub trend

FINDING #8093 · UNIT ID 1337918481

amitshekhariitbhu/llm-inference-engineering

Learn LLM Inference Engineering step by step - from KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.

[ MARKDOWN ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000157

ENGAGEMENT0.39

FRESHNESS1.31

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

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

32% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

2.50

ACCEL

+0.24

RETENTION

7.0%

PEAK 2026-08-20 · FORK-RETENTION 44.4% · 75 STARS / WINDOW

Author Audience

AUDIENCE

15,884

FOLLOWERS

8,725

OWNER ★

71,592

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 75 / 75 (DIVERSITY 1.00)

Why This Is A Finding

amitshekhariitbhu/llm-inference-engineering собрал 75 звёзд за окно, тогда как у автора всего 8,725 подписчиков — эффективная аудитория ≈ 15,884. Это даёт surprise-индекс 0.000157 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 44.4% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 16% OF 9595 FINDINGS

#1405emilkowalski/skills[ MARKDOWN ]0.0159 #1563Owl-Listener/designer-skills[ MARKDOWN ]0.0146 #3530jakubkrehel/make-interfaces-feel-better[ MARKDOWN ]0.00544 #4599JoseDeFreitas/awesome-youtubers[ MARKDOWN ]0.00333 #4729zenstory-ai/novel-to-game[ MARKDOWN ]0.00311

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9595 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 16%

VELOCITY2.503.67-1.17ABOVE 32%

RETENTION7.0%24.6%-17.6 PPABOVE 15%

FORKS26115-89ABOVE 19%

SURPRISE0.000.01-0.01ABOVE 6%