[Klaud Cold] Update qwen3.5-fp8-h200-sglang SGLang image to v0.5.12-cu130 (#1458)

* Update qwen3.5-fp8-h200-sglang SGLang image to v0.5.12-cu130

* chore: fill pr-link for #1458

Author: functionstackx

.github/configs/nvidia-master.yaml

@@ -3083,7 +3083,7 @@ dsv4-fp4-b300-vllm-mtp:
       - { tp: 4, ep: 4, dp-attn: true, conc-start: 256, conc-end: 512, spec-decoding: mtp }
 
 qwen3.5-fp8-h200-sglang:
-  image: lmsysorg/sglang:v0.5.9-cu129-amd64
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: Qwen/Qwen3.5-397B-A17B-FP8
   model-prefix: qwen3.5
   runner: h200

perf-changelog.yaml

@@ -2647,3 +2647,9 @@
   description:
     - "Update SGLang image from custom glm5-hopper tag (59d old) to v0.5.12-cu130"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1459
+
+- config-keys:
+    - qwen3.5-fp8-h200-sglang
+  description:
+    - "Update SGLang image from v0.5.9-cu129-amd64 (74d old) to v0.5.12-cu130"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1458