huggingface/ratchet

Minimum number of copies from `Uint8Array` to `wgpu::Buffer`

开放

#171 创建于 2024年4月18日

 (4 条评论) (1 个反应) (0 位负责人)Rust (44 个派生)auto 404
help wanted

仓库指标

星标
 (768 个星标)
PR 合并指标
 (PR 指标待抓取)

描述

Currently in wgpu, there is no way to create a wgpu::Buffer directly from Uint8Array.

This means that our tensor data does something like this:

IndexedDB -> Uint8Array -> Vec<u8> ~~> Uint8Array -> WebGPU

Judging by this: https://developer.mozilla.org/en-US/docs/Web/API/GPUBuffer

I think the optimal is:

IndexedDB -> Uint8Array -> WebGPU

Reference: https://github.com/gfx-rs/wgpu/blob/trunk/wgpu/src/backend/webgpu.rs#L1821

贡献者指南