mlcommons/training

Reference implementations of MLPerf® training benchmarks

Beginner friendly Everything

Open All

9 open issues indexed

LLM Post training - Question regarding seq-mask-tis and global_valid_toks denominator scaling. Open

mlcommons/training#905 · 3 comments · 1 assignee · Opened Sep 4, 2026
Reduce manual work from standardization of accelerator and host processor names Open

Fix for v6.1

mlcommons/training#886 · 6 comments · 1 assignee · Opened Jun 23, 2026
Review and minimize missed results in the results table, and UI submission failures Open

Fix for v6.1

mlcommons/training#877 · 4 comments · 1 assignee · Opened Jun 22, 2026
Downloaded data not displayed correctly in Excel/CSV format Open

mlcommons/training#845 · 1 comment · 1 reaction · 1 assignee · Opened Nov 24, 2025
Gres defaults to 8 regardless of config.sh Open

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

mlcommons/training#824 · Opened Aug 25, 2025
Git isn't initialized properly in `bash run_llama31.sh` Open

Difficulty 1/5 Under an hour Newbie friendliness 45/100

mlcommons/training#822 · 2 comments · Opened Aug 24, 2025
LLama 3.1 toml package missing Open

Difficulty 1/5 Under an hour Newbie friendliness 35/100

mlcommons/training#821 · 1 comment · Opened Aug 24, 2025
Llama 3.1 git: not a valid object name issue Open

Difficulty 2/5 1-3 hours Newbie friendliness 50/100

mlcommons/training#820 · 2 comments · Opened Aug 24, 2025
New reference benchmark development checklist Open

general

mlcommons/training#810 · 4 comments · 1 assignee · Opened Aug 1, 2025

Get new issues in your inbox