Skip to content

[PowerX] rate B300 HGX GPUs at 1,100 W in the power model port / [PowerX] 功耗模型移植版将 B300 HGX GPU 额定功耗改为 1,100 W - #1736

Merged
edwingao28 merged 1 commit into
mainfrom
fix/b300-power-model-tdp
Nov 10, 2026
Merged

edwingao28 merged 1 commit into
mainfrom
fix/b300-power-model-tdp

Conversation

@edwingao28

@edwingao28 edwingao28 commented Nov 9, 2026 •

Copy link
Copy Markdown
Collaborator

Summary

The power model port pins InferenceX power_model at 059bdc00e, where B300HGXBoard accepts only a 1,200 W GPU rating. The GPU registry (packages/constants/src/gpu-keys.ts) rates B300 at 1,100 W. So a B300 chart draws its Rated TDP line at 1,100 W while its modeled IT and PUE lines size fans for 1,200 W. For one B300 chassis at 100 W per GPU, idle, modeled IT power is 2,034.83 W at the old rating and 2,035.94 W at 1,100 W.

This ports SemiAnalysisAI/InferenceX#4960, which moves the upstream B300 rating to 1,100 W, the air-cooled HGX B300 figure.

Changes:

  • ubb/b300_hgx.ts: gpu_tdp_w defaults to and accepts only 1100, matching upstream b300_hgx.py.
  • hgx_fans.ts: HGX_FAN_BASELINE lists B300 at 1100 W and moves to version 2, matching upstream.
  • scripts/generate-power-model-parity.py: REVISION pins the upstream commit that carries the change.
  • power-model.manifest.json and power-model.parity.json: regenerated by that script, not edited by hand.
  • No UI, API or copy change. The Rated TDP line already used 1,100 W. Modeled B300 watts change only through fan power.

Testing:

  • vitest run over src/lib/power, src/components/inference, src/lib/charts, src/lib/views-api, src/lib/api, src/components/gpu-power and src/lib/powerx: 150 files, 4,962 tests passed, including power-model-parity.test.ts against the regenerated fixture.
  • Restoring 1,200 W in the port fails 339 parity cases, so the fixture pins the new rating.
  • lint, format and typecheck pass.

Blocker: REVISION points at the head of the unmerged upstream branch (95a63a2). After SemiAnalysisAI/InferenceX#4960 merges, re-pin REVISION to its merge commit and regenerate both files before merging this PR.

Related: Companion of SemiAnalysisAI/InferenceX#4960.

PR checklist
  • I have completed the AI model disclosure and kept it current
  • Added, changed, or removed filters, views, or pages include the matching API and inferencex-skills changes
  • New or changed indexable pages ship their /zh sibling
  • Changed Chinese copy follows the PR review checklist in docs/chinese-copy.md

Note

Low Risk
Localized power-model parity and B300 fan-sizing correction; no auth, API, or data-path changes beyond modeled watt estimates.

Overview
Aligns the TypeScript power model port with upstream InferenceX by rating B300 HGX at 1,100 W (air-cooled HGX spec) instead of 1,200 W, matching the app GPU registry and fixing the mismatch where charts drew Rated TDP at 1,100 W but modeled fans/IT power as if GPUs were 1,200 W.

B300HGXBoard now defaults to and accepts only gpu_tdp_w 1,100, and HGX_FAN_BASELINE moves to version 2 with B300 listed at 1,100 W so normalized fan sizing uses the same design heat. The parity generator’s REVISION is re-pinned to InferenceX commit 95a63a2 (carrying upstream PR 4960); power-model.manifest.json and power-model.parity.json were regenerated from that revision—no UI or API surface changes.

Reviewed by Cursor Bugbot for commit d7b4b3d. Bugbot is set up for automated code reviews on this repo. Configure here.

中文:功耗模型移植版将 B300 HGX 的 GPU 额定功耗改为 1,100 W,与上游 InferenceX power_model 保持一致。
@vercel

vercel Bot commented Nov 9, 2026 •

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated
inferencemax-app Ready Ready Preview Nov 9, 2026 10:12pm UTC

Request Review

@edwingao28
edwingao28 marked this pull request as ready for review November 10, 2026 01:00
@edwingao28
edwingao28 requested a review from adibarra as a code owner November 10, 2026 01:00
@edwingao28
edwingao28 merged commit da988f9 into main Nov 10, 2026
17 of 19 checks passed
@edwingao28
edwingao28 deleted the fix/b300-power-model-tdp branch November 10, 2026 01:00

This branch was successfully deployed

1 active deployment
Preview — d7b4b3db Deployed Nov 9, 2026 by vercel[bot]
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.

1 participant