diff --git a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/qwen3.5/sglang/h200-fp8/8k1k.yaml b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/qwen3.5/sglang/h200-fp8/8k1k.yaml
index 5c8b24c9d0..0b7c3761b9 100644
--- a/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/qwen3.5/sglang/h200-fp8/8k1k.yaml
+++ b/inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/qwen3.5/sglang/h200-fp8/8k1k.yaml
@@ -44,7 +44,7 @@ zip_override_concurrency:
   roles:
     agg:
       args:
-        cuda-graph-max-bs: [4, 8, 16, 32, 64]
+        cuda-graph-max-bs: [1, 2, 4, 8, 16, 32, 64, 128]
   benchmark:
     env:
-      CONC: ['4', '8', '16', '32', '64']
+      CONC: ['1', '2', '4', '8', '16', '32', '64', '128']
diff --git a/inferencex-e2e/configs/nvidia-master.yaml b/inferencex-e2e/configs/nvidia-master.yaml
index ceca84b4d9..5a4733aad7 100644
--- a/inferencex-e2e/configs/nvidia-master.yaml
+++ b/inferencex-e2e/configs/nvidia-master.yaml
@@ -1677,8 +1677,8 @@ qwen3.5-fp8-h200-sglang:
       search-space:
       - tp: 8
         ep: 8
-        conc-start: 4
-        conc-end: 64
+        conc-start: 1
+        conc-end: 128
         srt-recipe: 8k1k.yaml
 
 qwen3.5-fp8-h200-sglang-mtp:
diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml
index a9ee808acb..dbb276b4bb 100644
--- a/inferencex-e2e/perf-changelog.yaml
+++ b/inferencex-e2e/perf-changelog.yaml
@@ -10871,3 +10871,9 @@
     - "Update the vLLM ROCm image from v0.31.0 to v0.32.0."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4395
   scenario-type: [agentic-coding]
+
+- config-keys:
+    - qwen3.5-fp8-h200-sglang
+  description:
+    - "Extend TP8/EP8 8k1k concurrency from 4-64 to 1-128 (cuda-graph-max-bs follows concurrency)."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4415