ggml-org/llama.cpp

Question: How to generate an MPS gputrace

開放

#6,506 建立於 2024年4月5日

 (11 則留言) (0 個反應) (0 位負責人)C++ (21,812 個分叉)batch import
help wantedhigh priority

倉庫指標

星標
 (124,339 顆星)
PR 合併指標
 (平均合併 6天 8小時) (30 天內合併 389 個 PR)

描述

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

貢獻者指南