ggml-org/llama.cpp

ggml : add WebGPU backend

Fechada

#7.773 aberto em 5 de jun. de 2024

 (28 comentários) (23 reações) (0 responsável)C++ (21.822 forks)batch import
help wantedresearch 🔬roadmap

Métricas do repositório

Stars
 (124.374 estrelas)
Métricas de merge de PR
 (Mesclagem média 6d 8h) (389 fundiu PRs em 30d)

Description

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

Guia do colaborador