diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index 499d7f4b0a..9f23f94522 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -1734,7 +1734,7 @@ dsv4-fp4-b300-vllm-agentic-mtp:
       # TP8 GPU-resident + MTP (num_speculative_tokens=3)
       - { tp: 8, kv-offloading: none, spec-decoding: mtp, conc-list: [1, 4] }
       # TP4 GPU-resident + MTP (num_speculative_tokens=3)
-      - { tp: 4, kv-offloading: none, spec-decoding: mtp, conc-list: [8] }
+      - { tp: 4, kv-offloading: none, spec-decoding: mtp, conc-list: [1, 2, 4, 6, 8] }
       # TP4 SimpleCPU + MTP (num_speculative_tokens=3)
       - { tp: 4, kv-offloading: dram, kv-offload-backend: { name: vllm-simple }, spec-decoding: mtp, conc-list: [16] }
       # DEP4 SimpleCPU + MTP (num_speculative_tokens=3)
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 83136ac5d9..70522669d2 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6307,3 +6307,13 @@
     - "Disable TensorRT-LLM return_perf_metrics in the prefill and decode workers."
     - "Route the selected GB300 workloads to batch_3."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2690
+
+- config-keys:
+    - dsv4-fp4-b300-vllm-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Append GPU-resident TP4 concurrency 1, 2, 4, and 6 points to the existing B300 DeepSeek-V4-Pro vLLM AgentX MTP curve."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2647
+  append-only: true
+