diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 11fa1c1ce..989b2be34 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -1775,7 +1775,7 @@ 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:v0.5.14-cu130
+  image: lmsysorg/sglang:v0.5.19-cu130
   model: Qwen/Qwen3.5-397B-A17B-FP8
   model-prefix: qwen3.5
   runner: h200
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6d695e5b0..c6eb92f9e 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -7070,3 +7070,9 @@
     - "MTP draft length by concurrency: speculative-num-steps 3 (golden AL 2.49) below conc 256, and 1 (golden AL 1.79) at and above it."
     - "Trim the search space to TP8 no-offload conc [1, 4, 16], TP8 hicache conc [32, 48], and TP8 DP-attention hicache conc [128, 256]."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2885
+
+- config-keys:
+    - qwen3.5-fp8-h200-sglang
+  description:
+    - "Update SGLang image from lmsysorg/sglang:v0.5.14-cu130 to lmsysorg/sglang:v0.5.19-cu130 (digest sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9, tag commit sgl-project/sglang@0bcd822); recipe script, TP8/EP8 topology and the 8k1k concurrency range unchanged."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2965