[Perf] Qwen-Image Nightly Performance CI Improvement

[wtomin]

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

1. Inlined benchmark_params into test config files

Replaced all {"$ref": "benchmark_params.json"} references in test_qwen_image_sglang_diffusion.json and test_qwen_image_vllm_omni.json with the full inline parameter arrays (3 benchmark cases each: 512x512_steps20, 1536x1536_steps35, mixed_resolution).
Deleted tests/perf/tests/benchmark_params.json.

2. Populated baselines with real measured results

Extracted throughput_qps, latency_p99, peak_memory_mb_max, peak_memory_mb_mean from results.json for all 9 combinations (3 test cases × 3 benchmark params) and wrote them into the baseline blocks of test_qwen_image_vllm_omni.json.

3. Relocated tests/perf/ into tests/dfx/perf/

Used git mv to properly rename all three tracked files:
tests/perf/scripts/run_diffusion_benchmark.py → tests/dfx/perf/scripts/
tests/perf/tests/test_qwen_image_sglang_diffusion.json → tests/dfx/perf/tests/
tests/perf/tests/test_qwen_image_vllm_omni.json → tests/dfx/perf/tests/

Test Plan

Test Result

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan. Please provide the test scripts & test commands. Please state the reasons if your codes don't require additional test scripts. For test file guidelines, please check the test style doc
• The test results. Please paste the results comparison before and after, or the e2e results.
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model. Please run mkdocs serve to sync the documentation editions to ./docs.
• (Optional) Release notes update. If your change is user-facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

[wtomin]

@congw729 @yenuo26 @Gaohan123 @david6666666 @hsliuustc0106 PTAL.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 477702ab2c

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[congw729]

LGTM

[congw729]

Please rebase to the latest origin/main branch and the Doc failed builds will be resolved.

[Gaohan123]

LGTM