Skip to content

Add Training v6.1 column to the compatibility table - #224

Merged
ShriyaRishab merged 2 commits into
mlcommons:masterfrom
ShriyaRishab:shriya/new-round-v6.1
Aug 17, 2026
Merged

ShriyaRishab merged 2 commits into
mlcommons:masterfrom
ShriyaRishab:shriya/new-round-v6.1

Conversation

@ShriyaRishab

Copy link
Copy Markdown
Contributor

New Round: v6.1

Round chair: @ShriyaRishab
Prior round: v6.0
Submission deadline: Oct 16, 2026
Ruleset: 6.1.0

Tracking policies PR: mlcommons/training_policies#590

mlcommons/policies — compatibility table

  • Add a column for Training v6.1
  • Mark supported benchmarks for the new round (carry-forward plus Qwen3.5-397B-GRPO and DLRMv4-HSTU)
  • Mark all retired benchmarks as unsupported in the new column (llama3.1 405B, DLRM-dcnv2, and earlier retired models)

This PR

Adds a Training 6.1 column to MLPerf_Compatibility_Table.adoc.

  • Carry forward: LLama70B-LoRA, Llama3.1 8b, FLUX.1, DeepSeekv3, GPT-OSS-20B
  • New: Qwen3.5-397B-GRPO, DLRMv4-HSTU
  • Retired in 6.1: Llama3.1 405b, DLRM-dcnv2

Mark carry-forward benchmarks as comparable, retire llama3.1 405B and DLRM-DCNv2, and add Qwen3.5 GRPO and DLRMv4-HSTU.

Co-authored-by: Cursor <cursoragent@cursor.com>
@ShriyaRishab
ShriyaRishab requested a review from a team as a code owner August 14, 2026 19:16
@github-actions

Copy link
Copy Markdown

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

Comment thread MLPerf_Compatibility_Table.adoc
@ShriyaRishab
ShriyaRishab merged commit 45b8b62 into mlcommons:master Aug 17, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants