Add Kimi K2.5 INT4 vLLM benchmark for MI300X (TP8)

[functionstackx]

Closes #974

Add single-node MI300X config for Kimi K2.5 INT4 with vLLM ROCm v0.18.0, matching the existing MI325X recipe.

Generated with Claude Code

[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

[functionstackx]

@claude do v0.18.0 image..

[Klaud-Cold]

Claude finished @functionstackx's task in 1m 10s —— View job

---

Updated vLLM image to v0.18.0

• Read current files to identify image references
• Update image tag to v0.18.0 in amd-master.yaml
• Update perf-changelog.yaml description
• Commit and push changes

Updated the kimik2.5-int4-mi300x-vllm config image from vllm/vllm-openai-rocm:v0.16.0 to vllm/vllm-openai-rocm:v0.18.0 and updated the perf-changelog entry to match.
|

[benenzhu]

/usr/local/lib/python3.12/dist-packages/huggingface_hub/file_download.py:805: UserWarning: Not enough free disk space to download the file. The expected file size is: 9809.05 MB. The target location /mnt/hf_hub_cache/models--moonshotai--Kimi-K2.5/blobs only has 12.58 MB free disk space.

Seems the disk is full.

[functionstackx]

/usr/local/lib/python3.12/dist-packages/huggingface_hub/file_download.py:805: UserWarning: Not enough free disk space to download the file. The expected file size is: 9809.05 MB. The target location /mnt/hf_hub_cache/models--moonshotai--Kimi-K2.5/blobs only has 12.58 MB free disk space.

Seems the disk is full.

@cquil11 can u clean up the storage/ get more storage from AMD :sad: