diff --git a/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh
index 0fbe6619ab..c3d38e1b48 100755
--- a/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh
+++ b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh
@@ -14,12 +14,10 @@ if [[ -n "${SLURM_JOB_ID:-}" ]]; then
     echo "JOB $SLURM_JOB_ID running on ${SLURMD_NODENAME:-unknown}"
 fi
 
-if [ "$TP" -ne 8 ] || [ "$EP_SIZE" -ne 1 ] || [ "$DP_ATTENTION" != "false" ]; then
-    echo "This recipe requires TP=8, EP_SIZE=1, and DP_ATTENTION=false" >&2
-    exit 1
-fi
 require_agentic_kv_offload_none
 
+echo "Attention mode: $([ "$DP_ATTENTION" = "true" ] && echo dp || echo tp) (DP_ATTENTION=$DP_ATTENTION, CONC=$CONC)"
+
 if [[ -n "${ROCR_VISIBLE_DEVICES:-}" ]]; then
     export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
 fi
@@ -48,14 +46,37 @@ export ATOM_DEBUG_PREFIX_HITS=1
 export ATOM_PROFILER_MORE=0
 export ATOM_PROFILER_TIMEOUT=1200
 
-# AgentX/AIPerf network, failure, warmup, and trace-gap settings from the
-# validated one-hour baseline.
+# DP-attention runs layer ATOM's DPA routing and two-batch-overlap knobs on top of
+# the TP settings above (recipe section "Server - DP attention"); exported only for
+# the DP band. ATOM_DP_SESSION_AFFINITY is not optional: without it a session's
+# turns scatter across DP ranks, the prefix KV written by one turn is unreachable
+# by the next, and the multi-turn agentic workload collapses to cold prefill.
+# GPU_MAX_HW_QUEUES and ATOM_NUMA_BIND are prerequisites of --enable-tbo.
+DP_ATTN_ARGS=()
+if [ "$DP_ATTENTION" = "true" ]; then
+    export GPU_MAX_HW_QUEUES=5
+    export ATOM_NUMA_BIND=1
+    export ATOM_DP_SESSION_AFFINITY=1
+    export ATOM_DP_LB_REQ_EQUIV=512
+    export ATOM_ENABLE_PREFILL_DELAYER=1
+    export ATOM_PREFILL_DECODE_INTERVAL=10
+    # Client-side counterpart to session affinity: make AIPerf emit a stable
+    # session id (x-dynamo-session-id, falling back to the always-sent
+    # x-correlation-id) so the DPA router pins each conversation to one rank.
+    export AIPERF_HTTP_X_DYNAMO_SESSION_ID_FROM_CORRELATION_ID=true
+    export AIPERF_HTTP_X_SESSION_ID_FROM_CORRELATION_ID=true
+    DP_ATTN_ARGS=(--enable-dp-attention --enable-tbo)
+fi
+
+# Raise the AIPerf HTTP TCP user timeout to 900000 ms (15 min), well above the
+# aiperf default of 30000 ms (30 s), so long-stalling AgentX request
+# connections are not torn down as dead during extended server-side pauses.
 export AIPERF_HTTP_TCP_USER_TIMEOUT=900000
-export AIPERF_FAILED_REQUEST_THRESHOLD=0.10
-export AIPERF_LIVE_FAILED_REQUEST_THRESHOLD=0.10
-export AIPERF_TRACE_IDLE_GAP_CAP_SECONDS=300
-export AIPERF_WARMUP_REQUESTS_PER_LANE=10
-export AIPERF_BENCHMARK_GRACE_PERIOD=30
+export AIPERF_TIMING_CANCEL_DRAIN_TIMEOUT=300
+export AIPERF_DATASET_WEKA_LIVE_ASSISTANT_RESPONSES=0
+export AIPERF_DATASET_CONFIGURATION_TIMEOUT=1800
+export AIPERF_SERVICE_PROFILE_CONFIGURE_TIMEOUT=1800
+export AIPERF_UI_REALTIME_METRICS_ENABLED=true
 
 # Require ATOM Prometheus metrics in every official result.
 export AIPERF_SERVER_METRICS_URLS="http://localhost:${PORT}/metrics"
@@ -83,8 +104,7 @@ trap 'exit 143' TERM
 MAX_NUM_SEQS=$((2 * CONC))
 
 # golden_al_distribution/dsv4_mtp.yaml: thinking_on, 3 draft tokens -> AL 2.49
-# --spec-decode-acceptance-length 2.49.
-# https://github.com/ROCm/ATOM/pull/1948
+# https://github.com/SemiAnalysisAI/InferenceX/blob/main/golden_al_distribution/dsv4_mtp.yaml
 NUM_SPEC_TOKENS=3
 SPEC_DECODE_AL=2.49
 SPEC_ARGS=(
@@ -102,6 +122,12 @@ ATOM_CMD=(
     --served-model-name "$MODEL"
     --host 0.0.0.0
     --server-port "$PORT"
+    # uvicorn defaults to a 5s idle keep-alive; AIPerf pools sockets for far
+    # longer (aiohttp ~15s) and warmup inter-turn gaps under backlog exceed 5s,
+    # so the server closes an idle pooled socket and the reused write hits
+    # 'Connection reset by peer' (errno 104). One such reset on a root AgentX
+    # warmup request aborts the whole run. Outlast the client idle window.
+    --timeout-keep-alive 900
     --tensor-parallel-size "$TP"
     --kv-cache-dtype fp8
     --index-cache-dtype fp4
@@ -113,6 +139,7 @@ ATOM_CMD=(
     --level 3
     --cudagraph-mode FULL
     "${SPEC_ARGS[@]}"
+    "${DP_ATTN_ARGS[@]}"
     --max-num-seqs "$MAX_NUM_SEQS"
 )
 write_command "$RESULT_DIR/server_command.txt" "${ATOM_CMD[@]}"
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index 99f2aecfa4..ab36d1ce24 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1336,7 +1336,7 @@ dsv4-fp4-mi355x-vllm-agentic-mtp:
 # uses the thinking_on golden AL 2.49 for three draft tokens; eval uses real
 # MTP acceptance. max-num-seqs is set to 2x concurrency by the recipe.
 dsv4-fp4-mi355x-atom-agentic-mtp:
-  image: rocm/atom-dev:nightly_202608201032
+  image: rocm/atom-dev:nightly_202608280858
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: cluster:mi355x-amds
@@ -1346,7 +1346,8 @@ dsv4-fp4-mi355x-atom-agentic-mtp:
   scenarios:
     agentic-coding:
     - search-space:
-      - { tp: 8, ep: 1, dp-attn: false, kv-offloading: none, spec-decoding: mtp, conc-list: [1, 2, 4, 8, 16, 32, 48] }
+      - { tp: 8, ep: 1, dp-attn: false, kv-offloading: none, spec-decoding: mtp, conc-list: [1, 2, 4, 8, 16] }
+      - { tp: 8, ep: 1, dp-attn: true, kv-offloading: none, spec-decoding: mtp, conc-list: [48, 64, 96, 128, 256] }
 
 dsr1-fp4-mi355x-sglang-disagg-mtp:
   image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260519
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index e75a1ffdbf..a619ab7c7d 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6577,6 +6577,18 @@
     - "Runner: launch_gb300-nv.sh bumped from NVIDIA/srt-slurm@v1.0.29 to v1.0.72 for the dynamo-trt+qwen3.5+fp4 path."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2730
 
+- config-keys:
+    - dsv4-fp4-mi355x-atom-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Split the DeepSeek-V4-Pro FP4 ATOM AgentX MTP sweep into two attention bands per the ROCm/ATOM DeepSeek-V4-Agentic-InferenceX.md recipe: tensor-parallel attention at concurrency 1, 2, 4, 8, and 16, and DP attention at concurrency 48, 64, 96, 128, and 256 (previously a single tensor-parallel band at concurrency 1, 2, 4, 8, 16, 32, and 48)."
+    - "The DP-attention band adds --enable-dp-attention and --enable-tbo plus ATOM's DPA routing knobs (ATOM_DP_SESSION_AFFINITY, ATOM_DP_LB_REQ_EQUIV, ATOM_ENABLE_PREFILL_DELAYER, ATOM_PREFILL_DECODE_INTERVAL), the two-batch-overlap prerequisites GPU_MAX_HW_QUEUES and ATOM_NUMA_BIND, and the AIPerf session-affinity vars that keep each agentic conversation pinned to one DP rank; the tensor-parallel band is otherwise unchanged."
+    - "Session affinity is mandatory for the DP band: without it a session's turns scatter across DP ranks, the prefix KV written by one turn is unreachable by the next, and the multi-turn agentic workload collapses to cold prefill."
+    - "The attention band is selected by the config's dp-attn, propagated to the recipe as DP_ATTENTION, so the script's former DP_ATTENTION=false hard-fail guard is removed."
+    - "Bump the ATOM image from rocm/atom-dev:nightly_202608201032 to nightly_202608280858; FP8 KV/index caches, prefix caching, 32K state checkpoints, 16K batching/prefill chunks, FULL cudagraph mode, three-token MTP with golden AL 2.49, and max-num-seqs at twice concurrency are unchanged."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2778
+
 - config-keys:
     - dsv4-fp4-b200-sglang-agentic-hicache-mtp
   scenario-type: