ggml-org/llama.cpp

Question: How to generate an MPS gputrace

Open

#6,506 opened on Apr 5, 2024

View on GitHub
 (11 comments) (0 reactions) (0 assignees)C++ (18,202 forks)batch import
help wantedhigh priority

Repository metrics

Stars
 (110,169 stars)
PR merge metrics
 (Avg merge 6d 8h) (389 merged PRs in 30d)

Description

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

Contributor guide

Research direction
Investigate how to generate a GPU trace for Metal using Xcode's Metal Debugger or Instruments. Check the llama.cpp build system for Metal support and look for any existing documentation or scripts for profiling.
Tech stack
ccpp
Domain
backend
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
XcodeMetal Developer Tools
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65