diff --git a/.gitmodules b/.gitmodules
index b026356de5..1f1fade726 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,4 +1,4 @@
 [submodule "utils/aiperf"]
 	path = utils/aiperf
 	url = https://github.com/SemiAnalysisAI/aiperf.git
-	branch = cquil11/aiperf-agentx-v1.0
+	branch = cquil11/deterministic-agentic-warmup-count-main
diff --git a/benchmarks/benchmark_lib.sh b/benchmarks/benchmark_lib.sh
index c5e6fb2c86..413ac4e162 100644
--- a/benchmarks/benchmark_lib.sh
+++ b/benchmarks/benchmark_lib.sh
@@ -1744,14 +1744,13 @@ build_replay_cmd() {
     # utils/aiperf/docs/tutorials/agentx-mvp.md.
     local result_dir="$1"
     local duration="$DURATION"
-    local cache_warmup_duration="${AIPERF_AGENTIC_CACHE_WARMUP_DURATION:-600}"
+    local warmup_requests_per_lane="${AIPERF_WARMUP_REQUESTS_PER_LANE:-10}"
 
     # Fast mode is an e2e-only feedback preset used before canonical one-hour
     # sweeps. AIPerf already exposes both controls, so no AIPerf patch is
     # required.
     if [[ "${AIPERF_EXPERIMENTAL_FAST:-0}" == "1" ]]; then
         duration=1200
-        cache_warmup_duration=300
     fi
 
     export AIPERF_DATASET_WEKA_LIVE_ASSISTANT_RESPONSES="${AIPERF_DATASET_WEKA_LIVE_ASSISTANT_RESPONSES:-0}"
@@ -1765,6 +1764,9 @@ build_replay_cmd() {
     # aiperf validates that SERVICE_PROFILE_CONFIGURE_TIMEOUT >=
     # DATASET_CONFIGURATION_TIMEOUT at startup. Bump it in lockstep.
     export AIPERF_SERVICE_PROFILE_CONFIGURE_TIMEOUT=1800
+    # Headless realtime metrics are opt-in on current AIPerf main. Enable the
+    # rolling TTFT/ITL/throughput block and emit it every 30 seconds.
+    export AIPERF_UI_REALTIME_METRICS_ENABLED=true
     REPLAY_CMD="$AIPERF_CLI profile --scenario inferencex-agentx-mvp"
     REPLAY_CMD+=" --url http://localhost:$PORT"
     REPLAY_CMD+=" --endpoint /v1/chat/completions"
@@ -1773,6 +1775,7 @@ build_replay_cmd() {
     REPLAY_CMD+=" --model $MODEL"
     REPLAY_CMD+=" --concurrency $CONC"
     REPLAY_CMD+=" --benchmark-duration $duration"
+    REPLAY_CMD+=" --stats-interval 30"
     REPLAY_CMD+=" --random-seed 42"
     # Fail runs once more than 10% of requests error. This keeps known
     # transient low-rate failures from killing long sweeps while still
@@ -1784,10 +1787,11 @@ build_replay_cmd() {
     # least one profile turn after warmup.
     REPLAY_CMD+=" --trajectory-start-min-ratio 0.25"
     REPLAY_CMD+=" --trajectory-start-max-ratio 0.75"
-    # After the normal t* snapshot warmup, continue those exact trajectories
-    # with one-token outputs and no idle delays. Profiling begins only after
-    # those requests drain and resumes from the resulting live state.
-    REPLAY_CMD+=" --agentic-cache-warmup-duration $cache_warmup_duration"
+    # After the normal t* snapshot warmup, advance every trajectory lane by
+    # the same deterministic number of one-token requests with no idle delay.
+    # Profiling begins after those requests drain and resumes from the
+    # resulting live state.
+    REPLAY_CMD+=" --warmup-requests-per-lane $warmup_requests_per_lane"
     # Give long-context warmup requests up to 30 minutes to drain before
     # declaring warmup failed. Recipes whose saturation arms carry a larger
     # in-flight working set may override via AGENTIC_WARMUP_GRACE_PERIOD
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index ac1de53c7d..106073ac1c 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -5191,3 +5191,9 @@
     - "Agentic experiment Variant K (probe, of the #2374 Variant G): REMOVES the kimi-k3-container-deps.sh in-container patch (setup_script, script file, and launcher copy) to verify whether the mamba_hybrid index_fill_ dtype patch is still required by the current vllm/vllm-openai:kimi-k3 image — expected to fail at the first decode step if it is"
     - "Recipe: benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8pp2-agentic.yaml on the cluster:b200-dgxc pool"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2391
+
+- config-keys:
+    - kimik3-fp4-b300-vllm-agentic
+  description:
+    - "Test deterministic AIPerf warmup on Kimi K3 B300 with 10 requests per lane."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2408
diff --git a/utils/aiperf b/utils/aiperf
index 381758a88f..29749372a4 160000
--- a/utils/aiperf
+++ b/utils/aiperf
@@ -1 +1 @@
-Subproject commit 381758a88f5fa6335455ef5b0ded9557c1162814
+Subproject commit 29749372a46386280f9d049f8cbd8762f894b9a3