ggml-org/llama.cpp

ggml : add WebGPU backend

已关闭

#7,773 创建于 2024年6月5日

 (28 条评论) (23 个反应) (0 位负责人)C++ (21,786 个派生)batch import
help wantedresearch 🔬roadmap

仓库指标

星标
 (124,222 个星标)
PR 合并指标
 (平均合并 6天 8小时) (30 天内合并 389 个 PR)

描述

I hope that this would be relatively easy to do since AFAIK WebGPU allows us to write kernels in a shader language, so we have experience how to create such backends.

There has been some initial work in https://github.com/ggerganov/ggml/pull/585 - could be useful as a starting point

贡献者指南