经 AI Skill Hub 精选评估,分布式KV缓存调度与离loading库 获评「推荐使用」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
分布式KV缓存调度与离loading库 是一款基于 Go 开发的开源工具,专注于 installable、ai、go 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
分布式KV缓存调度与离loading库 是一款基于 Go 开发的开源工具,专注于 installable、ai、go 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:go install(推荐) go install github.com/llm-d/llm-d-kv-cache@latest # 方式二:从源码编译 git clone https://github.com/llm-d/llm-d-kv-cache cd llm-d-kv-cache go build -o llm-d-kv-cache . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/llm-d/llm-d-kv-cache/releases
# 查看帮助 llm-d-kv-cache --help # 基本运行 llm-d-kv-cache [options] <input> # 详细使用说明请查阅文档 # https://github.com/llm-d/llm-d-kv-cache
# llm-d-kv-cache 配置说明 # 查看配置选项 llm-d-kv-cache --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export LLM_D_KV_CACHE_CONFIG="/path/to/config.yml"
Efficiently caching Key & Value (KV) tensors is crucial for optimizing LLM inference. Reusing the KV-Cache, rather than recomputing it, significantly improves both Time To First Token (TTFT) and overall throughput, while also maximizing system resource-utilization. As a distributed LLM inference platform, llm-d provides a comprehensive suite of KV-Cache management capabilities to achieve these goals.
This repository contains the llm-d-kv-cache, a pluggable service designed to enable KV-Cache Aware Routing and lay the foundation for advanced, cross-node cache coordination in vLLM-based serving platforms.
The major component of this project is the KV-Cache Indexer is a high-performance library that keeps a global, near-real-time view of KV-Cache block locality across a fleet of vLLM pods.
It is powered by KVEvents streamed from vLLM, which provide structured metadata as KV-blocks are created or evicted from a vLLM instance's KV-cache. This allows the indexer to track which blocks reside on which nodes and on which tier (e.g., GPU or CPU). This metadata is the foundation for intelligent routing, enabling schedulers to make optimal, KV-cache-aware placement decisions.
The diagram below shows the primary data flows: the Read Path (scoring) and the Write Path (event ingestion).
Read Path: - 1: Scoring Request: A scheduler asks the KVCache Indexer to score a set of pods for a given prompt - 2: Index Query: The indexer calculates the necessary KV-block keys from the prompt and queries the KV-Block Index to see which pods have those blocks - 3: Return Scores: The indexer returns a map of pods and their corresponding KV-cache-hit scores to the scheduler
Write Path: - A: Event Ingestion: As vLLM pods create or evict KV-blocks, they emit KVEvents containing metadata about these changes - B: Index Update: The Event Subscriber consumes these events and updates the KV-Block Index in near-real-time
For a more detailed breakdown, please see the high-level Architecture and the Configuration docs.
-----
KVCache Indexer: A reference implementation showing how to run and use the kvcache.Indexer module KVCache Aware Scorer: A reference implementation of how to integrate the kvcache.Indexer into a scheduler like the llm-d-router * KV-Events: Demonstrates how the KV-Cache libraries handles KV-Events through both an offline example with a dummy ZMQ publisher and an online example using a vLLM Helm chart.
该项目提供了分布式KV缓存调度与离loading库,提高AI模型的性能和可靠性,但代码质量和文档需要进一步改进。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:分布式KV缓存调度与离loading库 的核心功能完整,质量良好。对于AI 技术爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | llm-d-kv-cache |
| 原始描述 | 开源AI工具:Distributed KV cache scheduling & offloading libraries。⭐149 · Go |
| Topics | installableaigo |
| GitHub | https://github.com/llm-d/llm-d-kv-cache |
| License | Apache-2.0 |
| 语言 | Go |
收录时间:2026-05-25 · 更新时间:2026-05-25 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。