Skip to main content

Python bindings for memcache_hybrid implemented with pybind11

Project description


High-performance distributed key-value cache

Docs PyPI PyPI - Python Version PyPI - Downloads GitCode commit activity license


🔄Latest News

  • [2025/12] MemCache已作为vllm-ascend backend使能大模型推理加速,详情查看vllm-ascend开源社区,使用示例

  • [2025/11] MemCache项目于2025年11月开源,开源社区地址为:https://gitcode.com/Ascend/memcache

🔜 Roadmap

MemCache roadmap和版本分支策略详见: Roadmap

🎉概述

MemCache是针对LLM推理、GR推理场景设计的高性能分布式KVCache存储引擎,其主要特性包括:

  • 基于对象操作的API:支持批量和非批量的put/get/exist/remove操作,支持多层结构的KV Block读写接口。
  • 支持多副本:单个对象支持多副本放置到不同的LocalService,默认是单副本,支持put接口指定副本数量。
  • 高带宽低时延:使用 MemFabric 作为多级内存和异构网络传输的底座,在Ascend硬件上,基于device_rdma(A2)、device_sdma(A3)、host_rdma(A2/A3) 等路径提供OneCopy跨机跨介质数据直接访问能力,满足高带宽,低时延的读写性能述求。在鲲鹏硬件上,支持host_urma(K5)。支持host_shm实现同节点共享内存通信。
  • 支持扩缩容:支持LocalService动态加入和移除
  • HA能力:在K8S集群中,MetaService支持多活能力,支持元数据恢复,提供尽力而为的HA能力。
architecture

🧩核心组件

MemCache包含LocalService和MetaService两大核心组件:

  • MetaService

    • 负责管理整个集群中内存池空间的分配和管理,处理LocalService的加入与退出。
    • MetaService作为独立进程运行,提供两种启动方式:python API启动;二进制启动,详见 安装部署
    • MetaService支持两种部署形态: 1、单点模式:MetaService由单个进程组成,部署方式简单,但存在单点故障的问题。如果MetaService进程崩溃或无法访问,系统将无法继续提供服务,直至重新恢复为止。 2、HA模式:该模式基于K8S的的ClusterIP Service和Lease资源构建,部署较为复杂,该模式会部署多个MetaService进程实例,实现多活高可用。部署详见 MetaService HA
  • LocalService:负责承担如下功能:

    • 客户端:作为客户端,以whl/so形式作为共享库被应用进程加载调用API
    • 内存提供者:负责提供一段连续的内存区域作为内存池空间的一部分,其内存可以被其他LocalService实例基于地址直接访问。

🔥性能表现

MemCache核心能力是提供大容量内存池和高性能的H2D、D2H、D2RH、RH2D数据访问能力,由于MemCache以 MemFabric 作为池化底座,所以支持RH2D、D2RH等OneCopy跨机跨介质数据直接访问能力,下图为RH2D对比其他中转路径的对比示意图。

RH2D

基于OneCopy跨机跨介质数据直接访问的能力,MemCache在A2/A3做了相关性能测试如下: 模拟构造DeepSeek-R1模型KV大小的block,单个block size为:61x128K + 61x16K = 8784KB ≈ 8.57MB,共122个离散地址。

  • 使用2个昇腾A2节点(每节点8张卡)组成双机内存池进行读写测试性能如下:
A2 perf
  • 使用2个昇腾A3节点(每节点8张卡16Die)组成双机内存池进行读写测试性能如下:
A3 perf

🔍目录结构

├── LICENSE                                 # LICENSE
├── .clang-format                           # 格式化配置
├── .gitmodules                             # git配置
├── .gitignore                              # git忽视配置文件
├── CMakeLists.txt                          # 项目的CMakeList
├── doc                                     # 文档目录
├── example                                 # 样例
│  ├── cpp                                  # c++样例
│  └── python                               # python样例
├── script                                  # 构建脚本
│  ├── build_and_pack_run.sh                # 编译+打包脚本
│  ├── build.sh                             # 编译脚本
│  ├── run_ut.sh                            # 编译+运行ut脚本
├── test                                    # test目录
│  ├── python                               # python测试用例
│  ├── k8s_deploy                           # k8s ha样例脚本
│  └── ut                                   # 单元测试用例
├── src                                     # 源码
│  ├── memcache                             # MemCache 源码
├── config                                  # 配置目录
│  ├── mmc-local.conf                       # 本地服务配置文件模板
│  ├── mmc-meta.conf                        # meta服务配置文件模板
├── README.md

🚀快速入门

请访问以下文档获取简易教程。

  • 编译部署:介绍组件编译和安装教程。
  • 配置文件:涉及MetaService、LocalService公共配置
  • 样例执行:介绍如何端到端执行样例代码,包括C++和Python样例。
  • [最佳实践]:推出中...

📑学习教程

  • c++接口:C++接口介绍以及C++接口对应的API列表
  • python接口:python接口介绍以及python接口对应的API列表

📦软件硬件配套说明

  • MemCache软件依赖 MemFabric,相关配套与MemFabric相同

📌FAQ

常见问题请参考:FAQ

📝相关信息

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

memcache_hybrid-1.1.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (4.0 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

memcache_hybrid-1.1.1-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (3.7 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

memcache_hybrid-1.1.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (4.0 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

memcache_hybrid-1.1.1-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (3.7 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

memcache_hybrid-1.1.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (4.0 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

memcache_hybrid-1.1.1-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (3.7 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

memcache_hybrid-1.1.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (4.0 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

memcache_hybrid-1.1.1-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (3.7 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

File details

Details for the file memcache_hybrid-1.1.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 d25469bb2ba56f5096924840e5b94d531e6ff5640882f5efcec976d99d1d8cc8
MD5 5419af21e5023c7bfdbbf6465b0a9eee
BLAKE2b-256 48bcea4d4fa9e9a505115973ab4100898dd1a2dc93f1459ff67dbc4212d9145d

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 9cd555394985a093a298aa34d909a6caf4a161fa3cfc76b3b68c3720e820c166
MD5 9d49938bd2fd4400af9dc0549fa60a9a
BLAKE2b-256 706ab4050d657b5b9811c7f0a258ef8db9295a466fd14bd6796333afc62a4ba8

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 c9e94ac3394f27850932960afcfc6fe241aa41bf895051d9d7bd4850980248e9
MD5 d1c3df7462d24e804e74e5a90355c61e
BLAKE2b-256 02337f74315fe9d3ecc087571865fea35dbf1379f329bcfb548865c259dbb9c2

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 aa8132f88e3c93eca2ad2419925917acfa2d8f6ee22f4ba2f460a08d1ff223ee
MD5 5a3ed46f14e3ad538bacc39128e0cb6e
BLAKE2b-256 266c392db90e1dec41a20cc443015043add49d4b9c9cafe19fb95735b17844ed

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 1da23f855879cd7fddd9e2d08e0692ee0bf9398daa4dc587c76f31777ba16be5
MD5 9938ccd68df2b98707bd6051540576a6
BLAKE2b-256 2aed2ad205511ff777c4d365bcf31d774a80f3de7b28519f19783a802e6dcf8c

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 64fdd340e92416c24985254c449a143d96f981ae3d945d5d1c57694f3948fa80
MD5 140a01482c21691ccc917c2a352dc2b9
BLAKE2b-256 155ccb31c17ea820ce177ff6dcbd7a8c889d57c82f8da139f78eb813c55346c2

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 cd0eb1ea9f25c2985b44d0e417bcea6a798fa4760b768bd9f817eed730a26480
MD5 353fa02f34aef9b8652d7054cb15b29d
BLAKE2b-256 4b9143e9a285161fa140ce51b442a4d40960e5138dab029e48b0156d6fc7a7aa

See more details on using hashes here.

File details

Details for the file memcache_hybrid-1.1.1-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for memcache_hybrid-1.1.1-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 8094a8fb68ff5dc91f0cbb7fc4692a9bbdd042fb610d793334381c4cc571f441
MD5 3e5c2675b35e099901e08c1ebad10031
BLAKE2b-256 51aef5627b0183b5d5d03fc70ba3d88c8b433b7417c73a429da9a6cc595ff07c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page