diff --git a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/mi355x-fp4-mtp/agentic.yaml b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/mi355x-fp4-mtp/agentic.yaml
index 826eaa1f0f..884971a138 100644
--- a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/mi355x-fp4-mtp/agentic.yaml
+++ b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/dsv4/sglang/mi355x-fp4-mtp/agentic.yaml
@@ -88,6 +88,7 @@ override_tp8_c1:
         max-running-requests: 2
         cuda-graph-max-bs-decode: 2
         cuda-graph-backend-prefill: breakable
+        enable-amd-monokernel: true
   benchmark:
     env:
       CONC: '1'
diff --git a/inferencex-e2e/configs/amd-master.yaml b/inferencex-e2e/configs/amd-master.yaml
index ed18bec2d6..fcb4c56fdf 100644
--- a/inferencex-e2e/configs/amd-master.yaml
+++ b/inferencex-e2e/configs/amd-master.yaml
@@ -1537,7 +1537,7 @@ glm5.2-fp4-mi355x-atom-agentic-mtp-mono:
       - { tp: 4, kv-offloading: none, conc-list: [1, 2], spec-decoding: mtp, srt-recipe: agentic.yaml }
 
 dsv4-fp4-mi355x-sglang-agentic-mtp:
-  image: lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261019
+  image: lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261028
   model: deepseek-ai/DeepSeek-V4-Pro-0813
   model-prefix: dsv4
   runner: cluster:mi355x-amds
diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml
index 18e8e72c5c..204002eebc 100644
--- a/inferencex-e2e/perf-changelog.yaml
+++ b/inferencex-e2e/perf-changelog.yaml
@@ -11556,3 +11556,12 @@
     - "Disagg: 6 DEP2 prefill workers with a DEP8 decode at conc 280-360 or a DEP16 decode at conc 300; DeepGEMM MegaMoE, NIXL transfer plus a shared MooncakeStore DRAM pool (160 GB per rank), Dynamo KV router."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4468
   scenario-type: [agentic-coding]
+
+- config-keys:
+    - dsv4-fp4-mi355x-sglang-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Bump to lmsysorg/sglang-rocm:v0.5.22-rocm720-mi35x-20261028."
+    - "Enable --enable-amd-monokernel at concurrency 1. Each DSpark verify there is one request's 7 tokens, which the monokernels run as one persistent launch per layer; steps with more rows run the standard forward."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4596