Skip to content

[PowerX] collect MiniMax-M3.1-Flash GB200 Dynamo-vLLM AgentX power / [PowerX] 采集 MiniMax-M3.1-Flash GB200 Dynamo-vLLM AgentX 功耗 - #4863

Open
edwingao28 wants to merge 2 commits into
mainfrom
chore/minimax-m31-gb200-power
Open

edwingao28 wants to merge 2 commits into
mainfrom
chore/minimax-m31-gb200-power

Conversation

@edwingao28

@edwingao28 edwingao28 commented Nov 6, 2026 •

Copy link
Copy Markdown
Collaborator

Summary

MiniMax-M3.1-Flash GB200 Dynamo-vLLM AgentX publishes no measured power: none of its 14 points (6 agg, 8 disagg) has valid power. Its latest curve (2026-11-01) comes from a run whose head predates #3670, which made multinode power collection default-on. This PR reruns the unchanged agg and disagg configs. Only the changelog changes, so infx.matrix.changed lists no keys.

Changes:

  • perf-changelog.yaml: one block listing both master keys of the curve, minimaxm31flash-fp4-gb200-dynamo-vllm-agentic-dspark-agg and minimaxm31flash-fp4-gb200-dynamo-vllm-agentic-dspark-disagg, so the sweep republishes the whole curve.
  • Expected power: GPU power from DCGM, plus Grace CPU power because gb200-nv declares cpu-power-exporter: {source: acpi}.
  • Both recipes place etcd and NATS on the infra node, not a dedicated one, so discovery_on_dedicated_node is false for all 14 variants and collection is not skipped.

No config, recipe or image changes.

Testing:

  • validate_perf_changelog passes. The planner emits 14 multinode throughput rows on cluster:gb200-nv and 11 AgentX eval rows.
  • In progress: full-sweep-fail-fast sweep 42200525155 of all 14 points at f3cf2b9.
PR checklist and change type

Type of Change

  • Bug fix
  • New feature
  • Configuration change
  • Documentation update
  • Other (please describe): rerun of unchanged configs to collect power

Checklist

  • I have completed the AI model disclosure and kept it current
  • I have tested my changes locally
  • I have updated documentation if necessary
  • If python -m infx.matrix.changed --base origin/main lists affected config keys, I have appended one new entry covering them to the physical end of inferencex-e2e/perf-changelog.yaml; if it lists none, I have added none. I have not edited historical entries
  • If this PR appends an inferencex-e2e/perf-changelog.yaml entry, it carries exactly one primary sweep label (a maintainer applies it on fork PRs): full-sweep-fail-fast (recommended), full-sweep-enabled, or non-canary-full-sweep-enabled. Optional modifiers all-evals, evals-only, and agentx-fast require a primary label; the last two block reuse while applied.
  • Before merging via reuse, an authorized maintainer (OWNER/MEMBER/COLLABORATOR) has commented /use <run_id> (or the legacy /reuse-sweep-run) on this PR. Do this only once there is a final full sweep that is all green with evals passing, since after this comment the primary sweep label will no longer automatically kick off new sweeps. Remove and re-add the primary sweep label to force a new sweep.

@github-actions

github-actions Bot commented Nov 6, 2026

Copy link
Copy Markdown
Contributor

Thanks for the contribution!

  • Review: If this PR changes files owned by someone other than a repository admin or @SemiAnalysisAI/core, ask one eligible CODEOWNER to complete the latest PR_REVIEW_CHECKLIST.md before contacting a core maintainer on Slack. Follow the template exactly, including As a PR reviewer and CODEOWNER, I have reviewed this and have, so sign-off verification triggers.
  • PR verification: Sweeps run only when the PR appends an inferencex-e2e/perf-changelog.yaml entry and carries exactly one primary label: full-sweep-fail-fast (strongly recommended; canary plus per-matrix fail-fast), full-sweep-enabled (canary; matrix jobs continue after a failure), or non-canary-full-sweep-enabled (no canary or fail-fast). The modifiers all-evals, evals-only, and agentx-fast require a primary label. On fork PRs, a maintainer applies the label. See sweep labels and reuse.
  • After merging: PR authors must ensure all GitHub Actions jobs pass. Transient failures often pass on rerun; see how to rerun failed jobs.
中文

感谢你的贡献!

  • **审阅:**如果 PR 修改的文件归属于仓库管理员及 @SemiAnalysisAI/core 之外的 CODEOWNER,请先联系一位有资格的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md,再通过 Slack 联系核心维护者。必须严格遵循模板,并保留 As a PR reviewer and CODEOWNER, I have reviewed this and have,才能触发签核验证。
  • **PR 验证:**只有当 PR 在 inferencex-e2e/perf-changelog.yaml 末尾追加了条目,并且恰好带有一个主标签时,才会运行扫描:full-sweep-fail-fast(强烈推荐;canary 加逐矩阵 fail-fast)、full-sweep-enabled(有 canary;矩阵任务在失败后继续运行)或 non-canary-full-sweep-enabled(无 canary,也无 fail-fast)。修饰标签 all-evals、evals-only 和 agentx-fast 必须与主标签一起使用。fork PR 的标签由维护者添加。参见扫描标签与复用。
  • **合并后:**PR 作者必须确保所有 GitHub Actions 任务通过。临时性失败通常可以通过重新运行恢复;参见重新运行失败任务的说明。

@edwingao28 edwingao28 added the full-sweep-fail-fast Full sweep with canary gate; first failure cancels the rest of that matrix (recommended) label Nov 6, 2026

@claude claude Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code review found no issues

No high-confidence issues detected in this change.

This review covers commit 5fee93e, which is no longer the latest commit on this pull request; later commits are not covered by it.

@github-actions

github-actions Bot commented Nov 6, 2026

Copy link
Copy Markdown
Contributor

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

full-sweep-fail-fast Full sweep with canary gate; first failure cancels the rest of that matrix (recommended)

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

1 participant