diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 67c996058..2245d3aef 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2632,7 +2632,7 @@ kimik2.5-int4-h200-vllm-agentic:
       - { tp: 8, offloading: cpu,  conc-list: [6, 7, 8, 9, 10, 11, 12, 13, 14] }
 
 kimik2.5-fp4-b200-vllm:
-  image: vllm/vllm-openai:v0.20.2
+  image: vllm/vllm-openai:v0.21.0
   model: nvidia/Kimi-K2.5-NVFP4
   model-prefix: kimik2.5
   runner: b200
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index cb92e0bf8..f4d7a4855 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -2882,3 +2882,9 @@
   description:
     - "Update SGLang image to v0.5.12-rocm700-mi35x"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1432
+
+- config-keys:
+    - kimik2.5-fp4-b200-vllm
+  description:
+    - "Update vLLM image from v0.20.2 to v0.21.0"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1504