amitshekhariitbhu/llm-inference-engineering — GitHub trend

FINDING #8190 · 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

SURPRISE0.000192

ENGAGEMENT0.64

FRESHNESS1.00

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

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

7% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

3.14

ACCEL

+0.39

RETENTION

57.1%

PEAK 2026-10-11 · FORK-RETENTION 0.0% · 22 STARS / WINDOW

Author Audience

AUDIENCE

16,296

FOLLOWERS

8,881

OWNER ★

74,154

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 22 / 22 (DIVERSITY 1.00)

Why This Is A Finding

amitshekhariitbhu/llm-inference-engineering собрал 22 звёзд за окно, тогда как у автора всего 8,881 подписчиков — эффективная аудитория ≈ 16,296. Это даёт surprise-индекс 0.000192 (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 16% OF 9747 FINDINGS

#271Vasik96/gtav-sourcecode-build-guide[ MARKDOWN ]0.0603 #942pallavi-shekhar/ai-engineering-interview-questions-company-wise[ MARKDOWN ]0.0224 #1664rebelytics/one-skill-to-rule-them-all[ MARKDOWN ]0.0127 #1882cbrock84/headcount[ MARKDOWN ]0.0112 #2400emilkowalski/skills[ MARKDOWN ]0.00831

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9747 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 16%

VELOCITY3.143.57-0.43ABOVE 44%

RETENTION57.1%33.3%+23.8 PPABOVE 82%

FORKS42104-62ABOVE 29%

SURPRISE0.000.01-0.01ABOVE 6%