华为详解 Kirin 9050 端侧运行 300 亿参数模型

华为周三详细介绍了 Kirin 9050 系列如何在无网络连接的情况下本地运行一个 300 亿参数的 AI 模型。该芯片全新的 Da Vinci 神经网络处理单元采用低比特量化,并协调内存与算力,从而在手机上运行该模型。
这一混合专家模型每次激活约 20 亿参数。华为此前在 10 月的芯片发布会上已披露该数字,本周又说明了同一处理器如何支持 AI 屏幕朗读、眼球追踪翻页等功能。[IT之家,中文] [10 月发布会,中文]
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(Huawei details how Kirin 9050 runs a 30-billion-parameter model on device)

Huawei on Wednesday detailed how the Kirin 9050 series runs a 30-billion-parameter AI model locally without an internet connection. The chip’s new Da Vinci neural processing unit uses low-bit quantization and coordinates memory and compute to run the model on a phone.
The mixture-of-experts model activates about 2 billion parameters at a time. Huawei previously disclosed that figure at its October chip briefing and this week described how the same processor supports features such as AI screen reading and eye-tracked page turning. [IT Home, in Chinese] [October briefing, in Chinese]
正文保留英文原文,标题与摘要由机器翻译。
原文发布于 TechNode(Huawei details how Kirin 9050 runs a 30-billion-parameter model on device),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。