ggml-org/llama.cpp

ggml : add DirectML backend

Open

#7,772 创建于 2024年6月5日

在 GitHub 查看
 (20 评论) (40 反应) (0 负责人)C++ (18,202 fork)batch import
help wantedresearch 🔬roadmap

仓库指标

Star
 (110,169 star)
PR 合并指标
 (平均合并 6天 8小时) (30 天内合并 389 个 PR)

描述

It seems like DirectML supports the upcoming NPU-enabled chips for Windows machines: https://devblogs.microsoft.com/directx/introducing-neural-processor-unit-npu-support-in-directml-developer-preview/

I don't think there is any other way to tap into this hardware, so we should explore if it possible to add this library as a backend in ggml in order to run stuff on the NPUs. There has been some semi-related work in the past that combined ggml and Direct3D: https://github.com/Const-me/Whisper. Not sure if it is relevant at all, maybe just as an inspiration

贡献者指南