Fix GPT-OSS ATOM config schema

[Oseltamivir]

No description provided.

[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

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]

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

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]

LGTM, mechanical schema fix bringing gptoss-fp4-mi355x-atom in line with the scenarios.fixed-seq-len structure used by every other entry in the file.

Extended reasoning...

Overview

This PR updates a single benchmark config entry (gptoss-fp4-mi355x-atom) in .github/configs/amd-master.yaml to use the scenarios.fixed-seq-len: schema. Previously this entry used a flat top-level seq-len-configs: key which doesn't match the schema used by every other entry in the same file. The numerical values (isl/osl/tp/ep/conc-start/conc-end) are preserved exactly.

Security risks

None. This is a benchmark configuration file consumed by CI, with no auth, crypto, or external-input handling implications.

Level of scrutiny

Low. The change is a mechanical structural fix to align one entry with the convention already used by ~30 other entries in the same file. There is no logic change.

Other factors

No bugs were flagged by the bug-hunter. Timeline contains only the auto recipe-reminder bot comments — no outstanding human review feedback. The companion commit 174a47c already landed a similar fix for the same entry, suggesting this is a routine schema correction.

[seungrokj]

@Oseltamivir thank you for fixing this. I missed this 👍