Revert "[AMD][MI300X] Expand GPT-OSS FP4 TP=1 concurrency from 64 to 256 (#1053)" [slip-sweep]

[cquil11]

Reverts #1053

A re-open PR with the same contents will follow.

[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://cookbook.sglang.io/
• https://docs.vllm.ai/projects/recipes/en/latest/

If it is not, please create a PR first before we can merge your 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/sgl-cookbook

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

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

[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://cookbook.sglang.io/
• https://docs.vllm.ai/projects/recipes/en/latest/

If it is not, please create a PR first before we can merge your 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/sgl-cookbook

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

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

[claude]

LGTM — simple mechanical revert of a concurrency config change, with the corresponding changelog entry removed.

Extended reasoning...

Overview

This PR reverts #1053, which had expanded the GPT-OSS FP4 MI300X vLLM TP=1 concurrency range from conc-end: 64 to conc-end: 256. The revert touches exactly two files: the AMD benchmark config YAML and the perf-changelog YAML, restoring both to their pre-#1053 state.

Security risks

None. These are benchmark configuration files controlling concurrency sweep parameters. No auth, crypto, or permission-sensitive code is involved.

Level of scrutiny

Low. This is a fully mechanical revert — the diff is a straightforward undo of the original change. The PR description notes a re-open will follow, consistent with a slip-sweep pattern used elsewhere in this repo.

Other factors

No bugs were found by the automated bug-hunting system. The timeline shows only bot comments. There are no outstanding reviewer concerns to address.