[Klaud Cold] Update gptoss-fp4-mi325x-vllm vLLM ROCm image to v0.21.0 (#1467)

* Update gptoss-fp4-mi325x-vllm vLLM ROCm image to v0.21.0

Update vLLM ROCm image from v0.17.0 (70d old) to v0.21.0

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: fill pr-link for #1467

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: claude-rebase-bot <claude-rebase-bot@local>

Author: 3 people

.github/configs/amd-master.yaml

@@ -872,7 +872,7 @@ gptoss-fp4-mi300x-vllm:
       - { tp: 8, conc-start: 1, conc-end: 16 }
 
 gptoss-fp4-mi325x-vllm:
-  image: vllm/vllm-openai-rocm:v0.17.0
+  image: vllm/vllm-openai-rocm:v0.21.0
   model: openai/gpt-oss-120b
   model-prefix: gptoss
   runner: mi325x

perf-changelog.yaml

@@ -2674,3 +2674,9 @@
   description:
     - "Update SGLang image from nightly-dev-20260216-d3bae71e (86d old) to v0.5.12-cu130"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1446
+
+- config-keys:
+    - gptoss-fp4-mi325x-vllm
+  description:
+    - "Update vLLM ROCm image from v0.17.0 (70d old) to v0.21.0"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1467