M3 mi325 profile run / MiniMax-M3 MI325X 性能剖析运行

Open
#1,765 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Quiet
Tech stack
python, pytorch
Domain
machine-learning, performance

Research direction

No file, test, or entry point is named. Start by locating the MI325X profiling and MiniMax-M3 execution path, then run the requested concurrency-4, single-decode-step profile. Done means a kernel-by-kernel wall-clock and percentage breakdown, including the MoE time and share.

Written by the indexing model from the issue text.

Description

@claude do a profile mi325 run with minimax m3 with conc 4, and for 1 decode step, breakdown where the time went kernel by kernel, wall clock time & %, how long did MoE take, etc?

中文说明

请求对 MiniMax-M3 在 MI325X 上进行性能剖析运行：并发度 4，针对单步解码，逐内核分解耗时（wall clock 时间和百分比），特别关注 MoE 层的耗时占比。

Dominant language
Python
Stars
1.7k
Forks
303
Avg merge
1d 13h
Merged PRs (30d)
284

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from SemiAnalysisAI/InferenceX

All issues in SemiAnalysisAI/InferenceX

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.