HackerNews中文版

大家好，今天我们推出了 QVAC SDK [0]，这是一个通用的 JavaScript/TypeScript SDK，旨在帮助开发者在桌面和移动设备上构建本地 AI 应用程序。该项目完全开源，采用 Apache 2.0 许可证。我们的目标是让开发者更容易构建有用的本地优先 AI 应用，而不必将许多不同的引擎、运行时和平台特定的集成拼凑在一起。SDK 的底层基于 QVAC Fabric [1]，这是我们的跨平台推理和微调引擎。 QVAC SDK 使用 Bare [2]，这是一个轻量级的跨平台 JavaScript 运行时，属于 Pear 生态系统的一部分。它几乎可以在任何地方作为工作线程使用，并内置了对 Node、Bun 和 React Native（Hermes）的工具支持。目前它支持的一些功能包括： ``` - 在桌面、移动设备和服务器上进行本地推理 - 支持大语言模型（LLMs）、光学字符识别（OCR）、翻译、转录、文本转语音和视觉模型 - 通过 Holepunch 堆栈 [4] 进行点对点模型分发，类似于 BitTorrent，任何人都可以成为播种者 - 基于插件的架构，便于添加新的引擎和模型类型 - 完全的点对点委托推理 ``` 我们还投入了大量精力来完善文档 [5]。文档的结构旨在便于人类和 AI 编码工具阅读，因此在实践中，您通常可以与您最喜欢的编码助手快速取得很大进展。我们知道还有一些地方需要改进： ``` - 当前的 Bare 插件打包效率不如预期，导致包体积大于我们希望的 - 插件工作流程可以更简单 - 虽然已经可以进行树摇，但目前仍需要 CLI 步骤，我们希望能使其更加自动化，并更好地集成到构建过程中 ``` 此次发布仅仅是个开始。我们希望帮助人们在更大规模上构建本地 AI。任何反馈都非常感谢！完整愿景可在官方网站 [6] 上查看。参考文献： [0] SDK: [http://qvac.tether.io/dev/sdk](http://qvac.tether.io/dev/sdk) [1] QVAC Fabric: [https://github.com/tetherto/qvac-fabric-llm.cpp](https://github.com/tetherto/qvac-fabric-llm.cpp) [2] Bare: [https://bare.pears.com](https://bare.pears.com) [3] Pear Runtime: [https://pears.com](https://pears.com) [4] Holepunch: [https://holepunch.to](https://holepunch.to) [5] 文档: [https://docs.qvac.tether.io](https://docs.qvac.tether.io) [6] 网站: [https://qvac.tether.io](https://qvac.tether.io)

查看原文

Hi folks, today we're launching QVAC SDK [0], a universal JavaScript/TypeScript SDK for building local AI applications across desktop and mobile.The project is fully open source under the Apache 2.0 license. Our goal is to make it easier for developers to build useful local-first AI apps without having to stitch together a lot of different engines, runtimes, and platform-specific integrations. Under the hood, the SDK is built on top of QVAC Fabric [1], our cross-platform inference and fine-tuning engine.QVAC SDK uses Bare [2], a lightweight cross-platform JavaScript runtime that is part of the Pear ecosystem [3]. It can be used as a worker pretty much anywhere, with built-in tooling for Node, Bun and React Native (Hermes).A few things it supports today:<pre><code> - Local inference across desktop, mobile and servers - Support for LLMs, OCR, translation, transcription, text-to-speech, and vision models - Peer-to-peer model distribution over the Holepunch stack [4], in a way that is similar to BitTorrent, where anyone can become a seeder - Plugin-based architecture, so new engines and model types can be added easily - Fully peer-to-peer delegated inference </code></pre> We also put a lot of effort into documentation [5]. The docs are structured to be readable by both humans and AI coding tools, so in practice you can often get pretty far with your favorite coding assistant very quickly.A few things we know still need work:<pre><code> - Bundle sizes are larger than we want right now because the current packaging of Bare add-ons is not as efficient as it should be yet - Plugin workflow can be simpler - Tree-shaking is already possible, but at the moment it still requires a CLI step, and we'd like to make that more automatic and better integrated into the build process </code></pre> This launch is only the beginning. We want to help people build local AI at a much larger scale. Any feedback is truly appreciated! Full vision is available on the official website [6].References:[0] SDK: <a href="http://qvac.tether.io/dev/sdk" rel="nofollow">http://qvac.tether.io/dev/sdk</a>[1] QVAC Fabric: <a href="https://github.com/tetherto/qvac-fabric-llm.cpp" rel="nofollow">https://github.com/tetherto/qvac-fabric-llm.cpp</a>[2] Bare: <a href="https://bare.pears.com" rel="nofollow">https://bare.pears.com</a>[3] Pear Runtime: <a href="https://pears.com" rel="nofollow">https://pears.com</a>[4] Holepunch: <a href="https://holepunch.to" rel="nofollow">https://holepunch.to</a>[5] Docs: <a href="https://docs.qvac.tether.io" rel="nofollow">https://docs.qvac.tether.io</a>[6] Website: <a href="https://qvac.tether.io" rel="nofollow">https://qvac.tether.io</a>

展示HN：QVAC SDK，一个用于构建本地AI应用的通用JavaScript SDK