diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 0a6c86df6..603e250fd 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -7461,7 +7461,7 @@ qwen3.5-fp8-h100-sglang-agentic-mtp:
 # the smaller part: TP8/EP8 rather than the cookbook's TP4/EP4, since 172.8 GiB
 # at TP4 leaves too little of an 80 GB card for the 256k-capped traces.
 qwen3.8next-fp8-h100-sglang-agentic-mtp:
-  image: lmsysorg/sglang:qwen38flashnext
+  image: lmsysorg/sglang:dev-cu13-qwen38-next-local@sha256:9d2a843c706c74bc259c0d9abf360551eb2734e1e7d255ab012a6965f10480b6
   model: Qwen/Qwen3.8-Flash-Next-FP8
   model-prefix: qwen3.8next
   runner: cluster:h100-dgxc
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6b249ea15..d431d13bb 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6921,3 +6921,11 @@
     - "Pick up the latest automatic ROCm DeepSeek-V4 optimizations, including fused mHC post/pre plus RMSNorm, gfx950 C4A top-k dispatch, fused C4 compressor GEMMs, fused SWA q/kv RMSNorm plus q FP8 quantization, and medium-batch cooperative top-k tuning."
     - "Keep the existing VLLM_ROCM_USE_AITER=1, VLLM_ROCM_USE_AITER_MOE=1, and --moe-backend aiter settings, and explicitly add VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=1 plus VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4 to both STP and MTP paths. The current checkpoint's shared-expert path does not satisfy the latest vLLM fusion conditions, so that fusion flag self-disables while preserving recipe parity."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2792
+
+- config-keys:
+    - qwen3.8next-fp8-h100-sglang-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Move the image from the mutable model-branch tag lmsysorg/sglang:qwen38flashnext (last re-pushed 2026-09-03T20:54:46Z, digest sha256:5ae5816783d58e2e56e84d2e863f5441425056f500b7fbd7448c4aae017a2521) to the newest Qwen3.8-Flash-Next model-branch build, lmsysorg/sglang:dev-cu13-qwen38-next-local@sha256:9d2a843c706c74bc259c0d9abf360551eb2734e1e7d255ab012a6965f10480b6 (Docker Hub last pushed 2026-09-07T11:12:42Z), pinned by digest so every node runs the same build. Qwen3.8-Flash-Next (architecture Qwen4ExpForConditionalGeneration) is not in SGLang main, v0.5.19, or the 2026-09-07 nightly (nightly-dev-cu13-20260907-30705c00), so no upstream nightly can serve it; the model-branch dev images are the only lineage. benchmarks/single_node/agentic/qwen3.8next_fp8_h100_mtp.sh is unchanged: TP8/EP8, mem-fraction 0.75, flashinfer attention (sm_90), native NEXTN MTP at three speculative tokens, float32 Mamba SSM state, golden thinking_on acceptance length 2.32; the conc [1, 4, 8, 12, 16] grid is unchanged. The sweep is the validation that this branch build still carries the fixes the recipe relies on."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2876