AI资讯大全AIPPXP.CN搜索 ↗
AI 快讯 · 自动更新

Epic update to local inference engine llama.cpp 1.0.0: Supports over 150 model architectures, and large models can run at full capacity even when offline.本地推理引擎 llama.cpp 1.0.0 史诗级更新:支持超 150 种模型架构,断网也能满血跑大模型

According to IT Home on 14 November, developer Georgi Gerganov (X account @ggerganov) posted a tweet on X yesterday (13 November), announcing the open-source AI inference project llama.cp…

IT之家 11 月 14 日消息,开发者 Georgi Gerganov(X 账号为 @ggerganov)昨日(11 月 13 日)在 X 平台发布推文, 宣布开源 AI 推理项目 llama.cp…

2026年11月14日 发布 · 1 分钟阅读 · 免费
本地推理引擎 llama.cpp 1.0.0 史诗级更新:支持超 150 种模型架构,断网也能满血跑大模型

Key Points要点速览

According to IT Home on 14 November, developer Georgi Gerganov (X account @ggerganov) posted on X yesterday (13 November), announcing that the open-source AI inference project llama.cpp and the library version of the underlying machine learning engine ggml have reached version 1.0.0. According to publicly available information obtained by IT Home, Gerganov is the creator of the open-source project llama.cpp, as well as a key developer of local AI foundational software such as ggml and whisper.cpp. In his personal X profile, he identifies himself as a Hugging Face engineer, and his GitHub profile lists his location as Sofia, Bulgaria. llama. cpp is an open-source AI inference project written primarily in C/C++. Its core function is to enable large language models to run on different hardware, such as personal computers and servers. It can be used for both local deployment and cloud services, with the aim of reducing deployment complexity and making full use of the device's computing power. The biggest highlight of this update is the clarification of interface compatibility rules: Project Library Positioning llama.cpp libllama C/C++ large model inference library ggml libggml Underlying machine learning tensor library Both will be upgraded in the future through major version numbers, clearly marking API or ABI incompatible changes, allowing applications that depend on these libraries to identify upgrade boundaries. For developers, it is easier to determine from the version number whether an upgrade may require their application to be modified in parallel. The official versioning rules are as follows: Version number When to update MAJOR, for example, 1.x.x → 2. 0.0 There are breaking changes to the public C API in ./include; the announcement also clarifies that API/ABI incompatibilities will be reflected in major version upgrades MINOR, e.g., 1.0.x → 1.1.0 Backward-compatible features, backend updates, model support, or API additions PATCH, e.g., 1.0.0 → 1.0.1 Bug fixes that do not change the API In terms of engineering quality, the official announcement states that in order to support the continuously accelerating pace of development, the team has emphasised three areas of investment: Using Hugging Face's HF Buckets and HF Jobs to expand the CI infrastructure. With hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM, and Intel, we are continuously expanding our self-hosted test runners to cover major hardware platforms. Use LLMs judiciously in the development process, while continuing to prioritise code quality, architectural control, and understanding of implementation details. In terms of backend and model support, ggml supports different hardware through dedicated backends; each backend can be compiled into a dynamic library and loaded at runtime as needed. llama.cpp already supports over 150 model architecture variants and mainstream speculative decoding methods. The team will also continue to strengthen its automated testing infrastructure and expand cross-platform test coverage with hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM, and Intel.

中文

IT之家 11 月 14 日消息,开发者 Georgi Gerganov(X 账号为 @ggerganov)昨日(11 月 13 日)在 X 平台发布推文, 宣布开源 AI 推理项目 llama.cpp 与底层机器学习引擎 ggml 的库版本迈入 1.0.0。 IT之家查询公开资料,Gerganov 是开源项目 llama.cpp 的创建者,也是 ggml、 whisper.cpp 等本地 AI 基础软件的重要开发者。他在个人 X 简介中将自己标注为 Hugging Face 工程师,GitHub 资料所在地为保加利亚索非亚。 llama.cpp 是一个主要用 C/C++ 编写的开源 AI 推理项目,核心作用是让大语言模型在个人电脑、服务器等不同硬件上运行。它既可以用于本地部署,也可以用于云端服务,目标是降低部署复杂度,并充分利用设备的计算能力。 本次更新最大的亮点就是明确接口兼容性规则: 项目 库 定位 llama.cpp libllama C/C++ 大模型推理库 ggml libggml 底层机器学习张量库 两者今后都会通过主版本号升级,明确标记 API 或 ABI 不兼容的变化,让依赖这些库的应用能够识别升级边界。对于开发者而言,可以从版本号上,更容易判断某次升级是否可能要求自己的应用同步修改。官方给出的版本规则是: 版本位 什么情况下更新 MAJOR,例如 1.x.x → 2.0.0 ./include 中公共 C API 出现破坏性变更;公告同时明确,API / ABI 不兼容会通过主版本升级体现 MINOR,例如 1.0.x → 1.1.0 向后兼容的功能、后端更新、模型支持或 API 新增 PATCH,例如 1.0.0 → 1.0.1 不改变 API 的 bug 修复 在工程质量方面,官方公告称为了支撑持续加快的开发节奏,团队强调了三项投入: 使用 Hugging Face 的 HF Buckets、HF Jobs 扩展 CI 基础设施。 在 NVIDIA、AMD、Qualcomm、Arm、IBM、Intel 的硬件支持下,持续增加覆盖主要硬件平台的自托管测试运行器。 在开发流程中审慎使用 LLM,同时继续把代码质量、架构控制和对实现细节的理解放在首位。 在后端与模型支持方面,ggml 通过专用后端支持不同硬件;每个后端都可以编译为动态库,并按需在运行时加载。 llama.cpp 已支持超过 150 种模型架构变体及主流推测解码方法。团队还将继续加强自动化测试基础设施,并借助英伟达、AMD、高通、Arm、IBM 和英特尔提供的硬件支持,扩大跨平台测试覆盖。

读完接着看 · Keep reading

想马上用起来?去「AI工具」栏挑一个直接下载,或在「AI教程」里跟着图文步骤做一遍。

去 AI工具 → 看 AI教程 →
0阅读0 条评论

阅读与点赞数据保存在你的浏览器本地,欢迎留下你的想法。

评论 文明发言,让讨论更有价值

正能量公益广告今日正能量学一点,用一点;今天种下的种子,会长成明天的能力。去免费下载专区 →广告