ggml-org/llama.cpp

Question: How to generate an MPS gputrace

Aperta

#6506 aperta il 5 apr 2024

 (11 commenti) (0 reazioni) (0 assegnatari)C++ (21.786 fork)batch import
help wantedhigh priority

Metriche repository

Star
 (124.222 stelle)
Metriche merge PR
 (Merge medio 6g 8h) (389 PR mergiate in 30 g)

Descrizione

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

Guida contributor