专属
文档
插件
助手
邀请
顶部
快速返回页面顶部
收起
收起工具栏
轩辕镜像 官方专业版
轩辕镜像
专业版
轩辕镜像 官方专业版
轩辕镜像
专业版
首页个人中心搜索镜像

交易
充值流量我的订单
工具
提交工单页面收录一键安装
Npm 源Pip 源Homebrew 源
帮助
常见问题轩辕镜像免费版
其他
关于我们网站地图
热门搜索:
ghcr.io/ggml-org/llama.cpp

ghcr.io/ggml-org/llama.cpp:full-b9265

ghcr.iolinux/amd64full-b9265大小: 未知更新于 2026年5月23日
让 AI 帮你使用轩辕镜像? · 展开查看说明

如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具,协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题,请先让 AI 阅读并遵守轩辕镜像的规则文档。

只需在 AI 对话中先发送下面这句话即可:

请先完整阅读并严格遵守以下文档中的全部规则与要求:

https://xuanyuan.cloud/agents.md

在未充分阅读并理解该文档前,不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。

查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式,不推荐豆包 AI;Cursor 等编辑器可在对话 @ 该链接,或加入 User Rules。 若 AI 无法访问外链,可 打开说明文档 复制全文粘贴。文档会随站点更新,复制内容可能过期,建议定期检查。

llama.cpp

C/C++实现的LLM推理

近期API变更

  • https://github.com/ggml-org/llama.cpp/issues/9289
  • https://github.com/ggml-org/llama.cpp/issues/9291

热门话题

  • Hugging Face 缓存迁移:使用 -hf 下载的模型现在存储在标准 Hugging Face 缓存目录中,可与其他 HF 工具共享。
  • https://github.com/ggml-org/llama.cpp/discussions/***
  • https://github.com/ggml-org/llama.cpp/discussions/***
  • https://github.com/ggml-org/llama.cpp/discussions/***
  • llama-server 现已支持多模态:https://github.com/ggml-org/llama.cpp/pull/*** | 文档
  • 用于 FIM 补全的 VS Code 扩展:https://github.com/ggml-org/llama.vscode
  • 用于 FIM 补全的 Vim/Neovim 插件:https://github.com/ggml-org/llama.vim
  • Hugging Face GGUF 编辑器:https://github.com/ggml-org/llama.cpp/discussions/9268 | 工具
  • 浏览器中现已支持 WebGPU,查看介绍博客/演示 https://reeselevine.github.io/llamas-on-the-web/%E3%80%82

快速开始

llama.cpp 的入门非常简单。以下是在您的机器上安装它的几种方法:

  • 使用 brew、nix 或 winget 安装 llama.cpp
  • 使用 Docker 运行 - 参见我们的 Docker 文档
  • 从 https://github.com/ggml-org/llama.cpp/releases 下载预构建二进制文件
  • 通过克隆此仓库从源代码构建 - 查看 我们的构建指南

安装完成后,您需要一个模型才能使用。请前往获取和量化模型部分了解更多信息。

示例命令:

# 使用本地模型文件
llama-cli -m my_model.gguf

# 或直接从 Hugging Face 下载并运行模型
llama-cli -hf ggml-org/gemma-3-1b-it-GGUF

# 启动兼容 OpenAI 的 API 服务器
llama-server -hf ggml-org/gemma-3-1b-it-GGUF

描述

llama.cpp 的主要目标是在各种硬件上(本地和云端)以最少的设置实现最先进的 LLM 推理性能。

  • 纯 C/C++ 实现,无任何依赖
  • Apple silicon 是一等公民——通过 ARM NEON、Accelerate 和 Metal 框架进行优化
  • x86 架构支持 AVX、AVX2、AVX512 和 AMX
  • RISC-V 架构支持 RVV、ZVFH、ZFH、ZICBOP 和 ZIHINTPAUSE
  • 1.5 位、2 位、3 位、4 位、5 位、6 位和 8 位整数量化,可实现更快的推理并减少内存使用
  • 用于在 NVIDIA GPU 上运行 LLM 的自定义 CUDA 内核(通过 HIP 支持 AMD GPU,通过 MUSA 支持摩尔线程 GPU)
  • Vulkan 和 SYCL 后端支持
  • CPU+GPU 混合推理,可部分加速大于总 VRAM 容量的模型

llama.cpp 项目是为 https://github.com/ggml-org/ggml 库开发新功能的主要实验场。

模型

通常也支持基于以下基础模型的微调模型。

添加新模型支持的说明:HOWTO-add-model.md

纯文本

  • LLaMA 🦙
  • LLaMA 2 🦙🦙
  • LLaMA 3 🦙🦙🦙
  • Mistral 7B
  • Mixtral MoE
  • DBRX
  • Jamba
  • Falcon
  • https://github.com/ymcui/Chinese-LLaMA-Alpaca 和 https://github.com/ymcui/Chinese-LLaMA-Alpaca-2
  • https://github.com/bofenghuang/vigogne
  • https://github.com/ggml-org/llama.cpp/pull/5423
  • Koala
  • Baichuan 1 & 2 + 衍生模型
  • Aquila 1 & 2
  • https://github.com/ggml-org/llama.cpp/pull/3187
  • Refact
  • https://github.com/ggml-org/llama.cpp/pull/3417
  • https://github.com/ggml-org/llama.cpp/pull/3553
  • Yi 模型
  • StableLM 模型
  • Deepseek 模型
  • Qwen 模型
  • https://github.com/ggml-org/llama.cpp/pull/3557
  • Phi 模型
  • https://github.com/ggml-org/llama.cpp/pull/***
  • GPT-2
  • https://github.com/ggml-org/llama.cpp/pull/5118
  • InternLM2
  • https://github.com/WisdomShell/codeshell
  • Gemma
  • https://github.com/state-spaces/mamba
  • Grok-1
  • Xverse
  • Command-R 模型
  • SEA-LION
  • GritLM-7B + GritLM-8x7B
  • OLMo
  • OLMo 2
  • OLMoE
  • Granite 模型
  • https://github.com/EleutherAI/gpt-neox + https://github.com/EleutherAI/pythia
  • ***-Arctic MoE
  • Smaug
  • Poro 34B
  • Bitnet b1.58 模型
  • Flan T5
  • Open Elm 模型
  • GLM-4-0414
  • SmolLM
  • EXAONE-3.0-7.8B-Instruct
  • FalconMamba 模型
  • Jais
  • Bielik-11B-v2.3
  • RWKV-7
  • https://github.com/BlinkDL/RWKV-LM
  • QRWKV-6
  • GigaChat-20B-A3B
  • Trillion-7B-preview
  • Ling 模型
  • LFM2 模型
  • Hunyuan 模型
  • BailingMoeV2(Ring/Ling 2.0)模型

多模态

  • LLaVA 1.5 模型、LLaVA 1.6 模型

  • BakLLaVA

  • Obsidian

  • ShareGPT4V

  • MobileVLM 1.7B/3B 模型

  • Yi-VL

  • Mini CPM

  • Moondream

  • https://github.com/BAAI-DCAI/Bunny

  • GLM-EDGE

  • Qwen2-VL

  • LFM2-VL

  • Python: https://github.com/ddh0/easy-llama

  • Python: https://github.com/abetlen/llama-cpp-python

  • Go: https://github.com/go-skynet/go-llama.cpp

  • Node.js: https://github.com/withcatai/node-llama-cpp

  • JS/TS(llama.cpp 服务器客户端): lgrammel/modelfusion

  • JS/TS(可编程提示引擎 CLI): https://github.com/offline-ai/cli

  • JavaScript/Wasm(可在浏览器中运行): https://github.com/tangledgroup/llama-cpp-wasm

  • Typescript/Wasm(更友好的 API,可在 npm 上获取): https://github.com/ngxson/wllama

  • Ruby: https://github.com/yoshoku/llama_cpp.rb

  • Ruby: https://github.com/docusealco/rllama

  • Rust(功能更丰富): https://github.com/edgenai/llama_cpp-rs

  • Rust(更友好的 API): https://github.com/mdrokz/rust-llama.cpp

  • Rust(更直接的绑定): https://github.com/utilityai/llama-cpp-rs

  • Rust(可从 crates.io 自动构建): https://github.com/ShelbyJenkins/llm_client

  • C#/.NET: https://github.com/SciSharp/LLamaSharp

  • C#/VB.NET(功能更丰富 - 社区许可证): LM-Kit.NET

  • Scala 3: https://github.com/donderom/llm4s

  • Clojure: https://github.com/phronmophobic/llama.clj

  • React Native: https://github.com/mybigday/llama.rn

  • Java: https://github.com/kherud/java-llama.cpp

  • Java: https://github.com/QuasarByte/llama-cpp-jna

  • Zig: https://github.com/Deins/llama.cpp.zig

  • Flutter/Dart: https://github.com/netdur/llama_cpp_dart

  • Flutter: https://github.com/xuegao-tzx/Fllama

  • PHP(基于 llama.cpp 构建的 API 绑定和功能): https://github.com/distantmagic/resonance https://github.com/ggml-org/llama.cpp/pull/6326

  • Guile Scheme: guile_llama_cpp

  • Swift: https://github.com/srgtuszy/llama-cpp-swift

  • Swift: https://github.com/ShenghaiWang/SwiftLlama

  • Delphi: https://github.com/Embarcadero/llama-cpp-delphi

  • Go(无需 CGo): https://github.com/hybridgroup/yzma

  • Android: llama.android

用户界面

(要在此处列出项目,该项目应明确说明其依赖于 llama.cpp)

  • https://github.com/yaroslavyaroslav/OpenAI-sublime-text%EF%BC%88MIT%EF%BC%89
  • BonzAI 应用(专有)
  • https://github.com/cztomsik/ava%EF%BC%88MIT%EF%BC%89
  • https://github.com/alexpinel/Dot%EF%BC%88GPL%EF%BC%89
  • https://github.com/ylsdamxssjxxdd/eva%EF%BC%88MIT%EF%BC%89
  • https://github.com/iohub/coLLaMA%EF%BC%88Apache-2.0%EF%BC%89
  • https://github.com/janhq/jan%EF%BC%88AGPL%EF%BC%89
  • https://github.com/johnbean393/Sidekick%EF%BC%88MIT%EF%BC%89
  • https://github.com/zhouwg/kantv?tab=readme-ov-file%EF%BC%88Apache-2.0%EF%BC%89
  • https://github.com/firatkiral/kodibot%EF%BC%88GPL%EF%BC%89
  • https://github.com/ggml-org/llama.vim%EF%BC%88MIT%EF%BC%89
  • https://github.com/abgulati/LARS%EF%BC%88AGPL%EF%BC%89
  • https://github.com/vietanhdev/llama-assistant%EF%BC%88GPL%EF%BC%89
  • https://github.com/undreamai/LlamaLib%EF%BC%88Apache-2.0%EF%BC%89
  • https://github.com/guinmoon/LLMFarm?tab=readme-ov-file%EF%BC%88MIT%EF%BC%89
  • https://github.com/undreamai/LLMUnity%EF%BC%88MIT%EF%BC%89
  • LMStudio(专有)
  • https://github.com/mudler/LocalAI%EF%BC%88MIT%EF%BC%89
  • https://github.com/LostRuins/koboldcpp%EF%BC%88AGPL%EF%BC%89
  • MindMac(专有)
  • https://github.com/MindWorkAI/AI-Studio%EF%BC%88FSL-1.1-MIT%EF%BC%89
  • https://github.com/Mobile-Artificial-Intelligence/maid%EF%BC%88MIT%EF%BC%89
  • https://github.com/Mozilla-Ocho/llamafile%EF%BC%88Apache-2.0%EF%BC%89
  • https://github.com/nat/openplayground%EF%BC%88MIT%EF%BC%89
  • https://github.com/nomic-ai/gpt4all%EF%BC%88MIT%EF%BC%89
  • https://github.com/ollama/ollama%EF%BC%88MIT%EF%BC%89
  • https://github.com/oobabooga/text-generation-webui%EF%BC%88AGPL%EF%BC%89
  • https://github.com/a-ghorbani/pocketpal-ai%EF%BC%88MIT%EF%BC%89
  • https://github.com/psugihara/FreeChat%EF%BC%88MIT%EF%BC%89
  • https://github.com/ptsochantaris/emeltal%EF%BC%88MIT%EF%BC%89
  • https://github.com/pythops/tenere%EF%BC%88AGPL%EF%BC%89
  • https://github.com/containers/ramalama%EF%BC%88MIT%EF%BC%89
  • https://github.com/semperai/amica%EF%BC%88MIT%EF%BC%89
  • https://github.com/withcatai/catai%EF%BC%88MIT%EF%BC%89
  • https://github.com/***89/autopen%EF%BC%88GPL%EF%BC%89

工具

  • https://github.com/akx/ggify – 从 Hugging Face Hub 下载 PyTorch 模型并将其转换为 GGML 格式
  • https://github.com/akx/ollama-dl – 从 Ollama 库下载模型以直接用于 llama.cpp
  • https://github.com/crashr/gppm – 启动 llama.cpp 实例,利用 NVIDIA Tesla P40 或 P100 GPU 降低空闲功耗
  • https://github.com/gpustack/gguf-parser-go/tree/main/cmd/gguf-parser - 查看/检查 GGUF 文件并估算内存使用情况
  • Styled Lines(专有许可,Unity3d 游戏开发推理部分的异步包装器,带有预构建的移动和 Web 平台包装器及模型示例)
  • https://github.com/unslothai/unsloth – 🦥 将微调及训练后的模型导出/保存为 GGUF 格式(Apache-2.0)

基础设施

  • https://github.com/intentee/paddler - 用于在自有基础设施中托管和扩展 AI 的开源 LLMOps 平台
  • https://github.com/gpustack/gpustack - 管理用于运行 LLM 的 GPU 集群
  • https://github.com/onicai/llama_cpp_canister - 在 Internet Computer 上作为智能合约的 llama.cpp,使用 WebAssembly
  • https://github.com/mostlygeek/llama-swap - 透明代理,通过 llama-server 添加自动模型切换功能
  • https://github.com/kalavai-net/kalavai-client - 众包端到端 LLM 部署,支持任意规模
  • https://github.com/InftyAI/llmaz - ☸️ 在 Kubernetes 上运行大型语言模型的简单、高级推理平台
  • https://github.com/defilantech/llmkube - 用于 llama.cpp 的 Kubernetes 算子,支持多 GPU 和 Apple Silicon Metal

llama-cli

一个用于访问和试验 llama.cpp 大部分功能的 CLI 工具。

以对话模式运行

具有内置聊天模板的模型会自动激活对话模式。如果未自动激活,可通过添加 -cnv 并使用 --chat-template NAME 指定合适的聊天模板来手动启用。

llama-cli -m model.gguf

#
> hi, who are you?
# Hi there! I'm your helpful assistant! I'm an AI-powered chatbot designed to assist and provide information to users like you. I'm here to help answer your questions, provide guidance, and offer support on a wide range of topics. I'm a friendly and knowledgeable AI, and I'm always happy to help with anything you need. What's on your mind, and how can I assist you today?
#
#
> what is 1+1?
# Easy peasy! The answer to 1+1 is... 2!

使用自定义聊天模板运行对话模式

# 使用 "chatml" 模板(使用 -h 查看支持的模板列表)
llama-cli -m model.gguf -cnv --chat-template chatml

# 使用自定义模板
llama-cli -m model.gguf -cnv --in-prefix 'User: ' --reverse-prompt 'User:'

使用自定义语法约束输出

llama-cli -m model.gguf -n 256 --grammar-file grammars/json.gbnf -p 'Request: schedule a call at 8pm; Command:'

# {"appointmentTime": "8pm", "appointmentDetails": "schedule a a call"}

grammars/ 文件夹包含一些示例语法。要编写自己的语法,请查看 GBNF 指南。

如需编写更复杂的 JSON 语法,请访问 [***]

llama-server

一个轻量级、与 https://github.com/openai/openai-openapi 兼容的 HTTP 服务器,用于部署 LLM。

使用默认配置在 8080 端口启动本地 HTTP 服务器

llama-server -m model.gguf --port 8080

# 可通过浏览器访问基本 Web UI:http://localhost:8080
# 聊天补全端点:http://localhost:8080/v1/chat/completions

支持多用户和并行解码

# 最多 4 个并发请求,每个请求最大上下文为 4096
llama-server -m model.gguf -c 16384 -np 4

启用推测解码

# draft.gguf 模型应为目标 model.gguf 的小型变体
llama-server -m model.gguf -md draft.gguf

部署嵌入模型

# 使用 /embedding 端点
llama-server -m model.gguf --embedding --pooling cls -ub 8192

部署重排序模型

# 使用 /reranking 端点
llama-server -m model.gguf --reranking

使用语法约束所有输出

# 自定义语法
llama-server -m model.gguf --grammar-file grammar.gbnf

# JSON
llama-server -m model.gguf --grammar-file grammars/json.gbnf

XCFramework

XCFramework 是适用于 iOS、visionOS、tvOS 和 macOS 的预编译库版本。它可用于 Swift 项目,无需从源代码编译库。例如:

// swift-tools-version: 5.10
// The swift-tools-version declares the minimum version of Swift required to build this package.

import PackageDescription

let package = Package(
name: "MyLlamaPackage",
targets: [
.executableTarget(
name: "MyLlamaPackage",
dependencies: [
"LlamaFramework"
]),
.binaryTarget(
name: "LlamaFramework",
url: "https://github.com/ggml-org/llama.cpp/releases/download/b5046/llama-b5046-xcframework.zip",
checksum: "c19be78b5f00d8d29a25da41042cb7afa094cbf6280a225abe614b03b20029ab"
)
]
)

上述示例使用的是库的中间构建版本 b5046。可以通过更改 URL 和校验和来修改为使用不同版本。

命令补全

部分环境支持命令行补全。

Bash 补全

$ build/bin/llama-cli --completion-bash
> ~/.llama-completion.bash
$ source ~/.llama-completion.bash

也可以选择将其添加到 .bashrc 或 .bash_profile 中以自动加载。例如:

$ echo "source ~/.llama-completion.bash"
>> ~/.bashrc

依赖项

  • https://github.com/yhirose/cpp-httplib - 单头文件 HTTP 服务器,供 llama-server 使用 - MIT license
  • https://github.com/nothings/stb - 单头文件图像格式解码器,供多模态子系统使用 - Public domain
  • https://github.com/nlohmann/json - 单头文件 JSON 库,供各种工具/示例使用 - MIT License
  • https://github.com/mackron/miniaudio - 单头文件音频格式解码器,供多模态子系统使用 - Public domain
  • https://github.com/sheredom/subprocess.h - 用于 C 和 C++ 的单头文件进程启动解决方案 - Public domain

轩辕镜像配置手册

按平台快速找到配置文档

Docker

登录仓库拉取

登录认证 · 私有仓库

专属域名拉取

免登录 · 高速拉取

Linux

Docker 镜像配置

Windows / Mac

Docker Desktop 配置

MacOS OrbStack

OrbStack 容器

Docker Compose

Compose 项目配置

NAS

群晖

Synology 配置

飞牛

fnOS 镜像配置

绿联

绿联 NAS

威联通

QNAP 配置

极空间

极空间 NAS

企业仓库

其他仓库

ghcr · Quay · nvcr

Harbor 镜像源

Proxy Repository 对接

Portainer 镜像源

Registries 配置

Nexus 镜像源

Docker Proxy 缓存

开发工具

Dev Containers

VS Code 开发容器

Podman

Podman 配置指南

Singularity / Apptainer

HPC 科学计算容器

Kubernetes

K8s Containerd

Kubernetes · Containerd

K3s

轻量级集群

面板 / 网络

爱快路由

iKuai 镜像加速

宝塔面板

一键配置镜像源

AI

用 AI 使用轩辕镜像

agents.md · AI 对话 · 提示词

需要其他帮助?请查看我们的 常见问题 Docker 镜像访问常见问题解答 或 提交工单

镜像拉取常见问题

功能

免费版与专业版区别

功能对比 · 版本选择

支持的镜像仓库

Docker Hub · GCR · GHCR

新手拉取配置

登录 · 专属域名 · 配置

docker search 限制

专属域名 · Hub 搜索

不支持 push

仅支持 pull · 不支持

拉取速度原因

带宽 · 缓存 · 冷热镜像

排错

402 与流量用尽

402 · 流量包 · 充值

401 认证失败

401 · docker login

manifest unknown

标签错误 · 镜像不存在

410 Gone 排查

410 · Docker 升级

429 限流

免费版 · 请求频率

DNS 超时

DNS 解析 · 网络超时

账号

失败是否计费

manifest · blob · 计费

申请开发票(企业 / 个人)

企业 · 个人 · 工单

修改登录密码

网站 · 仓库 · 重置

注销账户

工单 · 数据 · 注销

原理

mirrors 不生效

daemon.json · 重启

去掉域名前缀

docker tag · 重命名

指定架构拉取

ARM64 · AMD64 · 多架构

latest 与「最新」

digest · 版本号 · 标签

查看全部问题→

用户好评

来自真实用户的反馈,见证轩辕镜像的优质服务

用户头像

oldzhang

运维工程师

Linux服务器

5

"Docker访问体验非常流畅,大镜像也能快速完成下载。"

轩辕镜像
镜像详情
...
ghcr.io/ggml-org/llama.cpp
博客Docker 镜像公告与技术博客
热门查看热门 Docker 镜像推荐
教程轩辕镜像功能与使用教程
安装一键安装 Docker 并配置镜像源
官方公众号:源码跳动|官方技术交流群:13763429
官方公众号:源码跳动|官方技术交流群:|问题咨询请:提交工单
商务合作:点击复制邮箱
©2024-2026 源码跳动
商务合作:点击复制邮箱Copyright © 2024-2026 杭州源码跳动科技有限公司. All rights reserved.