diff --git a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p1d-dep8-dep32-c388-b4-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p1d-dep8-dep32-c388-b4-mtp.yaml
index d61fd88e0..92a4e0038 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p1d-dep8-dep32-c388-b4-mtp.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p1d-dep8-dep32-c388-b4-mtp.yaml
@@ -30,6 +30,7 @@ resources:
 backend:
   type: trtllm
   prefill_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -43,6 +44,7 @@ backend:
     PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
     CUDA_SCALE_LAUNCH_QUEUES: 4x
   decode_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -147,7 +149,6 @@ frontend:
     PRECISION: fp4
     CONC: '388'
     DURATION: '3600'
-    KV_OFFLOADING: none
     ETCD_LEASE_TTL: '120'
     DYN_ROUTER_QUEUE_THRESHOLD: None
     DYN_TOKENIZER_CACHE: '1'
@@ -173,7 +174,6 @@ benchmark:
     PRECISION: fp4
     CONC: '388'
     DURATION: '3600'
-    KV_OFFLOADING: none
     INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
     RESULT_DIR: /logs/agentic
     PORT: '8000'
diff --git a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p4d-dep4-tep8-c4-b1-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p4d-dep4-tep8-c4-b1-mtp.yaml
index cf82deb41..f8bd69f24 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p4d-dep4-tep8-c4-b1-mtp.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p4d-dep4-tep8-c4-b1-mtp.yaml
@@ -30,6 +30,7 @@ resources:
 backend:
   type: trtllm
   prefill_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -43,6 +44,7 @@ backend:
     PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
     CUDA_SCALE_LAUNCH_QUEUES: 4x
   decode_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -147,7 +149,6 @@ frontend:
     PRECISION: fp4
     CONC: '4'
     DURATION: '3600'
-    KV_OFFLOADING: none
     ETCD_LEASE_TTL: '120'
     DYN_ROUTER_QUEUE_THRESHOLD: None
     DYN_TOKENIZER_CACHE: '1'
@@ -173,7 +174,6 @@ benchmark:
     PRECISION: fp4
     CONC: '4'
     DURATION: '3600'
-    KV_OFFLOADING: none
     INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
     RESULT_DIR: /logs/agentic
     PORT: '8000'
diff --git a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p6d-dep4-tep4-c24-b4-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p6d-dep4-tep4-c24-b4-mtp.yaml
index 93836d384..2739536a4 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p6d-dep4-tep4-c24-b4-mtp.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-1p6d-dep4-tep4-c24-b4-mtp.yaml
@@ -30,6 +30,7 @@ resources:
 backend:
   type: trtllm
   prefill_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -43,6 +44,7 @@ backend:
     PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
     CUDA_SCALE_LAUNCH_QUEUES: 4x
   decode_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -147,7 +149,6 @@ frontend:
     PRECISION: fp4
     CONC: '24'
     DURATION: '3600'
-    KV_OFFLOADING: none
     ETCD_LEASE_TTL: '120'
     DYN_ROUTER_QUEUE_THRESHOLD: None
     DYN_TOKENIZER_CACHE: '1'
@@ -173,7 +174,6 @@ benchmark:
     PRECISION: fp4
     CONC: '24'
     DURATION: '3600'
-    KV_OFFLOADING: none
     INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
     RESULT_DIR: /logs/agentic
     PORT: '8000'
diff --git a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-2p1d-dep8-dep32-c736-b8-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-2p1d-dep8-dep32-c736-b8-mtp.yaml
index e2a5a5b38..963ffa7c5 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-2p1d-dep8-dep32-c736-b8-mtp.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-2p1d-dep8-dep32-c736-b8-mtp.yaml
@@ -30,6 +30,7 @@ resources:
 backend:
   type: trtllm
   prefill_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -43,6 +44,7 @@ backend:
     PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
     CUDA_SCALE_LAUNCH_QUEUES: 4x
   decode_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -148,7 +150,6 @@ frontend:
     PRECISION: fp4
     CONC: '736'
     DURATION: '3600'
-    KV_OFFLOADING: none
     ETCD_LEASE_TTL: '120'
     DYN_ROUTER_QUEUE_THRESHOLD: None
     DYN_TOKENIZER_CACHE: '1'
@@ -174,7 +175,6 @@ benchmark:
     PRECISION: fp4
     CONC: '736'
     DURATION: '3600'
-    KV_OFFLOADING: none
     INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
     RESULT_DIR: /logs/agentic
     PORT: '8000'
diff --git a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-3p1d-dep8-dep16-c1152-b32-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-3p1d-dep8-dep16-c1152-b32-mtp.yaml
index 0d40222e4..b3d4a9604 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-3p1d-dep8-dep16-c1152-b32-mtp.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-3p1d-dep8-dep16-c1152-b32-mtp.yaml
@@ -30,6 +30,7 @@ resources:
 backend:
   type: trtllm
   prefill_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -43,6 +44,7 @@ backend:
     PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
     CUDA_SCALE_LAUNCH_QUEUES: 4x
   decode_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -154,7 +156,6 @@ frontend:
     PRECISION: fp4
     CONC: '1152'
     DURATION: '3600'
-    KV_OFFLOADING: none
     ETCD_LEASE_TTL: '120'
     DYN_ROUTER_QUEUE_THRESHOLD: None
     DYN_TOKENIZER_CACHE: '1'
@@ -180,7 +181,6 @@ benchmark:
     PRECISION: fp4
     CONC: '1152'
     DURATION: '3600'
-    KV_OFFLOADING: none
     INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
     RESULT_DIR: /logs/agentic
     PORT: '8000'
diff --git a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-5p1d-dep8-dep16-c2626-b96-mtp.yaml b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-5p1d-dep8-dep16-c2626-b96-mtp.yaml
index d35338f15..9353b74ac 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-5p1d-dep8-dep16-c2626-b96-mtp.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/trtllm/deepseek-v4/agentx-gb300-20260811/dynamo-disagg-gb300-5p1d-dep8-dep16-c2626-b96-mtp.yaml
@@ -30,6 +30,7 @@ resources:
 backend:
   type: trtllm
   prefill_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -43,6 +44,7 @@ backend:
     PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
     CUDA_SCALE_LAUNCH_QUEUES: 4x
   decode_environment:
+    OMP_NUM_THREADS: '1'
     TLLM_LOG_LEVEL: INFO
     TRTLLM_SERVER_DISABLE_GC: '1'
     TRTLLM_WORKER_DISABLE_GC: '1'
@@ -170,7 +172,6 @@ frontend:
     PRECISION: fp4
     CONC: '2626'
     DURATION: '3600'
-    KV_OFFLOADING: none
     ETCD_LEASE_TTL: '120'
     DYN_ROUTER_QUEUE_THRESHOLD: None
     DYN_TOKENIZER_CACHE: '1'
@@ -196,7 +197,6 @@ benchmark:
     PRECISION: fp4
     CONC: '2626'
     DURATION: '3600'
-    KV_OFFLOADING: none
     INFMAX_CONTAINER_WORKSPACE: /infmax-workspace
     RESULT_DIR: /logs/agentic
     PORT: '8000'
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 9fcda3df3..8bbec03e0 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6547,3 +6547,12 @@
     - "Filter AgentX traces at the same 202,752-token context limit used by both TileRT roles so oversized Weka trajectories are excluded before replay."
     - "Pin SemiAnalysisAI/srt-slurm PR #10 commit d1e6c97b3baf3e87103b6d83189544c3c7d61c38, stacked on the AMD/native-router PR #7 and base runtime PR #1, including explicit native HTTP dependencies, GLM-5.1-compatible Transformers v5 router tokenization, incomplete-snapshot recovery, backend-declared conversion GPU resources, pre-container NVIDIA driver-hook activation, and lossless Slurm container-environment exports."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2750
+
+- config-keys:
+    - dsv4-fp4-gb300-dynamo-trt-agentx
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Set OMP_NUM_THREADS=1 for the prefill and decode workers across the GB300 Dynamo-TensorRT-LLM AgentX recipe matrix."
+    - "Allow the frontend and benchmark environments to inherit the runtime KV offloading setting."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2711