Revert "Add B300 config: kimi-k2.5-fp4-vllm (#1056)" [skip-sweep]

[cquil11]

Reverts #1056

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.

[claude]

LGTM — clean revert of the B300 Kimi-K2.5 FP4 vLLM config with no functional side-effects.

Extended reasoning...

Overview

This PR reverts #1056, which added a kimik2.5-fp4-b300-vllm benchmark configuration. Three files are touched: the YAML config entry is removed from .github/configs/nvidia-master.yaml, the benchmark shell script benchmarks/single_node/kimik2.5_fp4_b300.sh is deleted, and the corresponding perf-changelog entry is removed from perf-changelog.yaml. The author notes a follow-up re-open PR will come.

Security risks

None. The changes are purely config/script removal with no auth, crypto, or permission-sensitive code paths involved.

Level of scrutiny

Low. Reverts are among the simplest and lowest-risk PR types — the original change was already reviewed and merged, and this simply undoes it cleanly. No logic changes, no new code paths.

Other factors

No bugs were found by the automated system. The PR timeline shows only the standard bot reminder comment with no outstanding human reviewer concerns. The diff is mechanical and consistent with a standard git revert output.