[Klaud Cold] Update qwen3.5-fp4-b200-sglang (+mtp) SGLang image to v0.5.12-cu130 (#1474)

* Update qwen3.5-fp4-b200-sglang (+mtp) SGLang image to v0.5.12-cu130

Update SGLang image from nightly-dev-20260422-de962f32 (17d/13d old) to v0.5.12-cu130

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

* chore: fill pr-link for #1474

---------

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

Author: functionstackx

.github/configs/nvidia-master.yaml

@@ -2147,7 +2147,7 @@ qwen3.5-fp8-b200-sglang-agentic:
       - { tp: 8, ep: 1, offloading: none, conc-list: [1, 2, 4, 8, 16, 32] }
 
 qwen3.5-fp4-b200-sglang:
-  image: lmsysorg/sglang:nightly-dev-20260422-de962f32
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: nvidia/Qwen3.5-397B-A17B-NVFP4
   model-prefix: qwen3.5
   runner: b200
@@ -2168,7 +2168,7 @@ qwen3.5-fp4-b200-sglang:
       - { tp: 2, ep: 1, conc-start: 4, conc-end: 128 }
 
 qwen3.5-fp4-b200-sglang-mtp:
-  image: lmsysorg/sglang:nightly-dev-20260422-de962f32
+  image: lmsysorg/sglang:v0.5.12-cu130
   model: nvidia/Qwen3.5-397B-A17B-NVFP4
   model-prefix: qwen3.5
   runner: b200

perf-changelog.yaml

@@ -2776,3 +2776,10 @@
   description:
     - "Update vLLM image from v0.20.0-cu130 (20d/18d old) to v0.21.0"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1476
+
+- config-keys:
+    - qwen3.5-fp4-b200-sglang
+    - qwen3.5-fp4-b200-sglang-mtp
+  description:
+    - "Update SGLang image from nightly-dev-20260422-de962f32 (17d/13d old) to v0.5.12-cu130"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1474