ggml-org/llama.cpp

Question: How to generate an MPS gputrace

オープン

#6,506 opened on 2024/04/05

 (11 件のコメント) (0 件のリアクション) (0 人の担当者)C++ (21,812 件のフォーク)batch import
help wantedhigh priority

Repository metrics

Stars
 (124,339 個のスター)
PR merge metrics
 (平均マージ 6d 8h) (30d で 389 merged PRs)

説明

We're doing some work over at https://github.com/huggingface/candle to improve our Metal backend, I've been collecting various gputraces for the different frameworks and was wondering if there was a documented/known way to generate one for llama.cpp during model inference.

Specifically talking about this type of debugger output: https://developer.apple.com/documentation/xcode/metal-debugger

コントリビューターガイド