Update B200 Dsv4 configs

[wzhao18]

Note

Medium Risk
Changes the vLLM image pin and MoE/EPLB flags for DP-attention sweep points, which can shift measured throughput/latency and comparability to prior results.

Overview
Updates DeepSeek-V4 FP4 B200 vLLM benchmark serving so DP-attention search points turn on EPLB (expert parallel load balancing) with torch_nccl and synchronous EPLB, alongside the existing deep_gemm_mega_moe MoE backend in dsv4_fp4_b200_vllm.sh.

Pins the dsv4-fp4-b200-vllm config in nvidia-master.yaml to a specific vLLM nightly container image instead of v0.22.0, and records the EPLB change in perf-changelog.yaml.

^{Reviewed by Cursor Bugbot for commit 783dfe8. 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.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26899483031
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26899483031

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26900694153
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26900694153

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26900694153
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26900694153

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26905612623
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26905612623

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26905612623
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26905612623

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26914041013
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26914041013

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26914041013
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26914041013

[wzhao18]

@kedarpotdar-nv @functionstackx @Oseltamivir Ready for review/merge. Thanks!