diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 2cd991028..495567729 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2685,7 +2685,7 @@ kimik2.5-fp4-b200-vllm-agentic:
 # Kimi-K2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available.
 
 kimik2.5-fp4-b300-vllm:
-  image: vllm/vllm-openai:v0.19.0-cu130
+  image: vllm/vllm-openai:v0.21.0
   model: nvidia/Kimi-K2.5-NVFP4
   model-prefix: kimik2.5
   runner: b300
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 48e20a9b2..19bb076fd 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -2729,3 +2729,9 @@
   description:
     - "Add MTP/EAGLE speculative-decoding sibling of qwen3.5-bf16-mi325x-sglang"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1483
+
+- config-keys:
+    - kimik2.5-fp4-b300-vllm
+  description:
+    - "Update vLLM image from v0.19.0-cu130 (27d old) to v0.21.0"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1452