diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index f8cc486b2..c7c92a700 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -8270,7 +8270,7 @@ kimik2.5-fp4-gb200-dynamo-trt:
           dp-attn: true
 
 kimik2.5-fp4-gb200-dynamo-vllm:
-  image: vllm/vllm-openai:v0.18.0-cu130
+  image: vllm/vllm-openai:v0.21.0
   model: nvidia/Kimi-K2.5-NVFP4
   model-prefix: kimik2.5
   runner: gb200
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index b7182a39c..25ac8f78f 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -3192,3 +3192,10 @@
     - "Add GLM-5-FP8 models.yaml flags, setup_deps.sh (aiter gluon + transformers glm_moe_dsa), GLM-5 env tuning in env.sh"
     - "Add multinode launch script glm5_fp8_mi355x_sglang-disagg.sh; server.sh sources setup_deps.sh"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1572
+
+- config-keys:
+    - kimik2.5-fp4-gb200-dynamo-vllm
+  description:
+    - "Bump vLLM image from vllm/vllm-openai:v0.18.0-cu130 to vllm/vllm-openai:v0.21.0"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1582
+