diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index bc1e7f517..526fbec48 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -7544,7 +7544,7 @@ qwen3.8next-fp8-h200-sglang-agentic-mtp:
 # H200 AgentX MTP frontier with DRAM HiCache. This is intentionally an MTP-only
 # submission; the model's non-speculative AgentX arm is not included.
 qwen3.5-fp8-h200-sglang-agentic-hicache-mtp:
-  image: lmsysorg/sglang:nightly-dev-cu13-20260907-30705c00
+  image: lmsysorg/sglang:v0.5.19-cu130
   model: Qwen/Qwen3.5-397B-A17B-FP8
   model-prefix: qwen3.5
   runner: cluster:h200-dgxc
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 792e237fb..b0dc6a14d 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -7138,3 +7138,10 @@
     - "Pin vLLM nightly-9ea8f3ffc354901b740f0b31988900897b7221d7, Dynamo 1.5.0.dev20260908, and NVIDIA/srt-slurm d50ee7280c33d469df8708e363e23be2456e94fb."
     - "Use Dynamo-native MiniMax parsing, EAGLE3 with FlashInfer, FULL_AND_PIECEWISE CUDA graphs, and wait for the OpenAI chat route before AgentX trace replay."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2925
+
+- config-keys:
+    - qwen3.5-fp8-h200-sglang-agentic-hicache-mtp
+  description:
+    - "Update SGLang image from lmsysorg/sglang:nightly-dev-cu13-20260907-30705c00 (2026-09-07 cu13 dev nightly, build commit sgl-project/sglang@30705c00) to the v0.5.19 release image lmsysorg/sglang:v0.5.19-cu130 (digest sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9, build commit sgl-project/sglang@0bcd822377da7b5718e674eaf9c870d349424dd1, Docker Hub last pushed 2026-09-04T22:50:19Z)."
+    - "The release image ships the same CUDA 13.0.3, FlashInfer 0.6.18 and sgl-kernel 0.4.6.post1 as the nightly. benchmarks/single_node/agentic/qwen3.5_fp8_h200_mtp.sh is unchanged: SGLANG_ENABLE_SPEC_V2 EAGLE MTP at 3 steps, golden acceptance length 3.39, flashinfer attention with allreduce fusion, fp8 quantization and fp8_e4m3 KV, HiCache kernel IO / page_first layout. TP8/EP1 DRAM HiCache concurrency 2 through 24 unchanged."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2966