Update DSv4 B200 TRT image to 2dd03e6 (non-MTP + MTP)

[Oseltamivir]

Summary

• Point dsv4-fp4-b200-trt and dsv4-fp4-b200-trt-mtp at ghcr.io/semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-2dd03e6, replacing the older 9aa3715 build.
• Tighten concurrency search space to fit B200 memory ceiling (1k1k max 128, 8k1k max 256).

Test plan

• Sweep fires on push (37 single_node jobs + 6 evals, all B200)
• Pure-TP (dpa=false) jobs pass
• Attention-DP (dpa=true) jobs pass at capped concurrency

---

Note

Low Risk
Benchmark-only image tag and sweep bound changes in master config and changelog; no application runtime or auth paths.

Overview
Updates B200 DeepSeek-V4-Pro TensorRT-LLM benchmark configs (dsv4-fp4-b200-trt and dsv4-fp4-b200-trt-mtp) to use container image feat-deepseek_v4-2dd03e6 instead of 9aa3715.

Concurrency sweeps for attention-DP (ep: 8, dp-attn: true) are capped lower so jobs stay within B200 memory: 1k/1k EP runs now stop at 128 (was up to 2048/512 for MTP), and 8k/1k at 256 (was up to 1024). Pure-TP ranges are unchanged.

Documents the change in perf-changelog.yaml for both config keys.

^{Reviewed by Cursor Bugbot for commit 7baa914. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

• https://docs.sglang.io/cookbook/intro
• https://recipes.vllm.ai/

If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sglang/tree/main/docs_new

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

[claude]

🟡 The new perf-changelog entry at line 3467 still has the pull/PENDING placeholder instead of pull/1664 — this will merge as a broken changelog link, breaking the convention used by every other entry in the file. Additionally, the description bullet only documents the image switch and omits the substantial attention-DP concurrency search-space reduction also in this PR (trt 1k1k 2048→128, trt 8k1k 1024→256, trt-mtp 1k1k 512→128); the file consistently documents such changes alongside image bumps (see lines 56, 81, 447, 2236). Both fixes are trivial — replace PENDING with 1664 and add a second bullet noting the concurrency tightening.

Extended reasoning...

Issue 1 — pr-link: .../pull/PENDING

The diff adds at perf-changelog.yaml:3467:

  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/PENDING

This is PR #1664, but the URL was left as the literal placeholder PENDING. As written, the link resolves to https://github.com/SemiAnalysisAI/InferenceX/pull/PENDING, which is a 404.

Step-by-step proof. The three entries immediately preceding this one (added in PRs #1641, #1647, #1648) all use concrete integer PR numbers in their pr-link field — e.g. lines 3439, 3446, 3453, 3460. Grepping perf-changelog.yaml for pull/PENDING matches only this new entry; every other one of the ~hundred entries uses a real PR number. So this is unambiguously a forgotten placeholder, not a stylistic choice.

Issue 2 — concurrency search-space changes omitted from description

The PR makes two substantive behavioral changes:

1. Image switch (documented in the new bullet).
2. Attention-DP concurrency upper-bound tightening, not documented:
   • dsv4-fp4-b200-trt 1k1k: conc-end: 2048 → 128
   • dsv4-fp4-b200-trt 8k1k: conc-end: 1024 → 256
   • dsv4-fp4-b200-trt-mtp 1k1k: conc-end: 512 → 128

Future readers of perf-changelog.yaml will not see that the sweep grid shrank and that previously-benchmarked high concurrencies (256–2048) are no longer covered.

Why this is a real gap, not subjective. The refutation argues that what to put in a changelog is an editorial call and the PR-description framing treats concurrency as a supporting change. That is a fair concern, but the established convention in this specific file repeatedly documents concurrency search-space changes alongside image bumps, e.g.:

• L56: "Extend concurrency to 128 for gptoss mi355x/b200"
• L81: "Increase concurrency for some configurations" — paired with a TRT image bump on L80 for dsr1-fp8-h200-trt, an exact parallel to this PR
• L447: "Extend maximum concurrency to 256 across all sequence lengths"
• L2236: "Raise conc-end from 64 to 256..."

The PR description itself ("Tighten concurrency search space to fit B200 memory ceiling") and the Cursor-Bugbot summary both call this out as a distinct change. Omitting it from perf-changelog.yaml is a genuine divergence from how the file is maintained — not just style.

Impact and fix

Neither issue affects runtime/benchmark behavior; both are changelog-metadata cleanups, hence nit severity. Suggested fix:

- config-keys:
    - dsv4-fp4-b200-trt
    - dsv4-fp4-b200-trt-mtp
  description:
    - "Use official TRT-LLM release image (nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc15.post1) for B200 DeepSeek-V4-Pro TRT configs, replacing the custom ghcr.io feat/deepseek_v4 build (9aa3715)."
    - "Tighten attention-DP concurrency search space to fit B200 memory: 1k1k conc-end 2048→128 (trt) / 512→128 (trt-mtp); 8k1k conc-end 1024→256 (trt)."
  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1664

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26969952142
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26969952142

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26987679137
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26987679137

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=27000571018
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=27000571018