Revert "Add Kimi K2.5 INT4 single-node MI325X vLLM benchmark (TP8)"

[cquil11]

Reverts #857

[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

[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

[claude]

LGTM, clean revert of a benchmark config addition.

Extended reasoning...

Overview

This PR is a GitHub-generated revert of PR #857, which had added the Kimi K2.5 INT4 single-node MI325X vLLM benchmark (TP8). The changes remove: (1) the kimik2.5-int4-mi325x-vllm config block from .github/configs/amd-master.yaml, (2) the benchmark shell script benchmarks/single_node/kimik2.5_int4_mi325x.sh, and (3) the corresponding changelog entry from perf-changelog.yaml.

Security risks

None. The PR only removes benchmark configuration and a benchmark launch script. No authentication, permissions, or sensitive data handling is involved.

Level of scrutiny

Low scrutiny is appropriate. This is a mechanical, auto-generated revert that purely removes config entries and a shell script. The git log on master already shows the corresponding revert commit (7208bbc), confirming this is an intentional rollback.

Other factors

No outstanding reviewer comments exist (only automated bot messages). No bugs were found. The diff is self-contained and does not affect any shared infrastructure or production code paths — only benchmark definitions.