diff --git a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/dsv4/trtllm/gb300-fp4/agentx/disagg-variants.yaml b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/dsv4/trtllm/gb300-fp4/agentx/disagg-variants.yaml
index 7608b30e92..6d01e494bf 100644
--- a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/dsv4/trtllm/gb300-fp4/agentx/disagg-variants.yaml
+++ b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/dsv4/trtllm/gb300-fp4/agentx/disagg-variants.yaml
@@ -6,12 +6,14 @@ base:
     model: {}
     container: {}
     frameworks:
-      tensorrt_llm: 1.3.0rc24
+      tensorrt_llm: 1.4.0rc1
   dynamo:
     install: true
     source:
-      git: https://github.com/cquil11/dynamo.git
-      rev: 2cbbdc863c336c2cfffa2a3668e2a6661801b259
+      # Upstream v1.6.1: resolves interface-name DYN_TCP_RPC_HOST (ai-dynamo/dynamo#11870)
+      # and decouples TRT-LLM KV events from metrics (ai-dynamo/dynamo#12162).
+      # Prebuilt wheels: a source build's cudarc 0.19.8 rejects the image's CUDA 13.4.
+      pypi: "1.6.1"
     request_plane: tcp
   health_check:
     max_attempts: 1440
@@ -56,6 +58,9 @@ base:
           event_buffer_max_size: 0
           free_gpu_memory_fraction: 0.8
           host_cache_size: 193273528320
+          # 1.4.0rc1 always enforces the SWA scratch resize check (debug-only in 1.3.0rc24),
+          # which c388 prefill tripped; DeepSeek-V4 model defaults turn scratch reuse on.
+          enable_swa_scratch_reuse: false
           pool_ratio:
             - 0.55
             - 0.22
diff --git a/inferencex-e2e/configs/nvidia-master.yaml b/inferencex-e2e/configs/nvidia-master.yaml
index ba48d18e77..93f5f2e8b0 100644
--- a/inferencex-e2e/configs/nvidia-master.yaml
+++ b/inferencex-e2e/configs/nvidia-master.yaml
@@ -6591,7 +6591,7 @@ kimik3-fp4-gb200-dynamo-vllm-agentic-mooncake-dcp16-agg:
           dp-attn: false
 
 dsv4-fp4-gb300-dynamo-trt-agentx:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc24
+  image: nvcr.io/nvidia/tensorrt-llm/release:1.4.0rc1@sha256:3bedbe0321e7eb5430f3177d88894a3cf2dc2f6a087d0e85c13fc882667c75c0
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: cluster:gb300-nv
diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml
index 18e8e72c5c..e272285a32 100644
--- a/inferencex-e2e/perf-changelog.yaml
+++ b/inferencex-e2e/perf-changelog.yaml
@@ -11556,3 +11556,10 @@
     - "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-gb300-dynamo-trt-agentx
+  description:
+    - "Update the TensorRT-LLM image from 1.3.0rc24 to 1.4.0rc1 and the recipe Dynamo pin to v1.6.1."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4583
+  scenario-type: [agentic-coding]