huggingface/ratchet

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

開放

#171 建立於 2024年4月18日

 (4 則留言) (1 個反應) (0 位負責人)Rust (44 個分叉)auto 404
help wanted

倉庫指標

星標
 (768 顆星)
PR 合併指標
 (30 天內沒有已合併 PR)

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

貢獻者指南