vllm-marconi-offload

Skilluncategorisedvllmkv-cacheprefix-cacheoffload

Two-tier (RAM + SSD) KV cache offload connector for vLLM with Marconi-style reuse-aware eviction.

Directory Presence

Cross-referenced across 55 tracked directories

Directory	Status	First Seen	Last Confirmed	Link
P PyPI (Real-time)		5/24/2026	7/25/2026
P PyPI Skills Registry		7/24/2026	7/24/2026

#9068

Popularity Rank

1 / 55

Listed In

Emerging

Adoption Stage

5/24/2026

First Seen

Recently added to the ecosystem

9/100

Directory Presence5/20

Community0/30

Usage0/20

Development Activity4/30

The official Python library for the anthropic API

Skilluncategorised

4K4 dirs

BerriAI

Library to easily interface with LLM API providers

Skilluncategorised

62K4 dirs

Unclecode

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper

Skilluncategorised

86K4 dirs

ekuttan

Claude Code skill that generates structured product knowledge bases from codebase scanning

Skilluncategorised

103 dirs