---
title: "kvcached"
type: "tool"
slug: "ovg-project-kvcached"
canonical_url: "https://www.graphcanon.com/tools/ovg-project-kvcached"
github_url: "https://github.com/ovg-project/kvcached"
homepage_url: null
stars: 1093
forks: 122
primary_language: "Python"
license: "Apache-2.0"
archived: false
categories: ["llm-frameworks", "inference-serving"]
tags: ["kvcache-optimization", "llm", "kvcached", "elastic-kvcache", "gpu-mutiplexing", "inference-engine", "gpu-sharing", "kvcache"]
updated_at: "2026-07-12T02:16:34.385929+00:00"
---

# kvcached

> Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

## Facts

- Repository: https://github.com/ovg-project/kvcached
- Stars: 1,093 · Forks: 122 · Open issues: 90 · Watchers: 10
- Primary language: Python
- License: Apache-2.0
- Last pushed: 2026-07-02T05:33:52+00:00

## Trust & health

_Signals computed from public GitHub metadata. Not a security guarantee._

- Maintenance: Active (computed 2026-07-11T11:43:56.934Z)
- Security scan: No lockfile (0 critical, 0 high, 0 medium, 0 low) · last scan 2026-07-11T11:43:57.439Z
- Full report: [trust report](/tools/ovg-project-kvcached/trust.md) · [JSON](https://www.graphcanon.com/api/graphcanon/tools/ovg-project-kvcached/trust)

## Categories

- [LLM Frameworks](/categories/llm-frameworks.md)
- [Inference & Serving](/categories/inference-serving.md)

## Tags

kvcache-optimization, llm, kvcached, elastic-kvcache, gpu-mutiplexing, inference-engine, gpu-sharing, kvcache

## Category neighbours (exploratory)

_Same-category tools for discovery only - not curated alternatives. Cap shown at six._

- [airllm](/tools/lyogavin-airllm.md) - AirLLM 70B inference with single 4GB GPU (★ 22,399) [Very active]
- [skypilot](/tools/skypilot-org-skypilot.md) - Run, manage, and scale AI workloads on any AI infrastructure. (★ 10,285) [Very active]
- [Liger-Kernel](/tools/linkedin-liger-kernel.md) - Efficient Triton Kernels for LLM Training (★ 6,494) [Very active]
- [Awesome-LLM-Compression](/tools/huangowen-awesome-llm-compression.md) - Awesome LLM compression research papers and tools to accelerate LLM training and inference. (★ 1,848) [Active]
- [KVarN](/tools/huawei-csl-kvarn.md) - KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag. (★ 435) [Active]
- [LLMKube](/tools/defilantech-llmkube.md) - Kubernetes operator for self-hosted LLM inference across various GPU types (★ 163) [Very active]

_+ 1 more not listed._

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/ovg-project-kvcached`](/api/graphcanon/tools/ovg-project-kvcached)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_