diff --git a/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh
new file mode 100755
index 000000000..0fbe6619a
--- /dev/null
+++ b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh
@@ -0,0 +1,132 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set -x
+
+# Agentic trace replay benchmark for DeepSeek-V4-Pro FP4 on MI355X using
+# ATOM MTP. Throughput runs use the committed golden synthetic acceptance;
+# eval-only runs use the model's real MTP acceptance.
+
+source "$(dirname "$0")/../../benchmark_lib.sh"
+
+check_env_vars MODEL TP CONC KV_OFFLOADING TOTAL_CPU_DRAM_GB RESULT_DIR DURATION EP_SIZE DP_ATTENTION
+
+if [[ -n "${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
+
+if [[ -n "${ROCR_VISIBLE_DEVICES:-}" ]]; then
+    export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
+fi
+
+if [[ -n "${MODEL_PATH:-}" ]]; then
+    if [[ ! -d "$MODEL_PATH" || -z "$(ls -A "$MODEL_PATH" 2>/dev/null)" ]]; then
+        hf download "$MODEL" --local-dir "$MODEL_PATH"
+    fi
+else
+    hf download "$MODEL"
+    export MODEL_PATH="$MODEL"
+fi
+
+rocm-smi || true
+amd-smi || true
+
+resolve_trace_source
+install_agentic_deps
+
+# ATOM runtime settings validated with the DeepSeek-V4-Pro AgentX baseline.
+export AITER_BF16_FP8_MOE_BOUND=0
+export AITER_LOG_LEVEL=WARNING
+export ATOM_MOE_GU_ITLV=1
+export ATOM_DISABLE_MMAP=true
+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.
+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
+
+# Require ATOM Prometheus metrics in every official result.
+export AIPERF_SERVER_METRICS_URLS="http://localhost:${PORT}/metrics"
+export AIPERF_REQUIRED_SERVER_METRIC_PREFIX="atom:"
+
+wait_for_amd_gpu_clean
+
+SERVER_LOG="$RESULT_DIR/server.log"
+mkdir -p "$RESULT_DIR"
+
+SERVER_PID=""
+cleanup_atom_server() {
+    local exit_code=$?
+    trap - EXIT INT TERM
+    set +e
+    stop_background_process_tree "$SERVER_PID" "ATOM server" 60
+    exit "$exit_code"
+}
+trap cleanup_atom_server EXIT
+trap 'exit 130' INT
+trap 'exit 143' TERM
+
+# AgentX concurrency counts session trees. Keep 2x scheduler headroom for the
+# request bursts produced by subagent fan-out.
+MAX_NUM_SEQS=$((2 * CONC))
+
+# golden_al_distribution/dsv4_mtp.yaml: thinking_on, 3 draft tokens -> AL 2.49
+# --spec-decode-acceptance-length 2.49.
+# https://github.com/ROCm/ATOM/pull/1948
+NUM_SPEC_TOKENS=3
+SPEC_DECODE_AL=2.49
+SPEC_ARGS=(
+    --method mtp
+    --num-speculative-tokens "$NUM_SPEC_TOKENS"
+)
+if [ "${EVAL_ONLY:-false}" != "true" ]; then
+    SPEC_ARGS+=(--spec-decode-acceptance-length "$SPEC_DECODE_AL")
+fi
+
+echo "Starting ATOM server with MAX_NUM_SEQS=$MAX_NUM_SEQS NUM_SPEC_TOKENS=$NUM_SPEC_TOKENS SPEC_DECODE_AL=$SPEC_DECODE_AL EVAL_ONLY=${EVAL_ONLY:-false}"
+ATOM_CMD=(
+    python3 -u -m atom.entrypoints.openai_server
+    --model "$MODEL_PATH"
+    --served-model-name "$MODEL"
+    --host 0.0.0.0
+    --server-port "$PORT"
+    --tensor-parallel-size "$TP"
+    --kv-cache-dtype fp8
+    --index-cache-dtype fp4
+    --enable-prefix-caching
+    --gpu-memory-utilization 0.9
+    --max-num-batched-tokens 16384
+    --attn-prefill-chunk-size 16384
+    --state-checkpoint-interval-tokens 8192
+    --level 3
+    --cudagraph-mode FULL
+    "${SPEC_ARGS[@]}"
+    --max-num-seqs "$MAX_NUM_SEQS"
+)
+write_command "$RESULT_DIR/server_command.txt" "${ATOM_CMD[@]}"
+"${ATOM_CMD[@]}" > "$SERVER_LOG" 2>&1 &
+SERVER_PID=$!
+echo "Server PID: $SERVER_PID"
+
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+if [ "${EVAL_ONLY:-false}" = "true" ]; then
+    run_eval --port "$PORT"
+else
+    # AgentX DSv4 traces already carry fully formed chat payloads; do not apply
+    # AIPerf's generic chat template on top of them.
+    build_replay_cmd "$RESULT_DIR"
+    run_agentic_replay_and_write_outputs "$RESULT_DIR"
+fi
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index 59f655945..10604c32b 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1284,6 +1284,22 @@ dsv4-fp4-mi355x-vllm-agentic-mtp:
       # while MTP creates two. Restore these points after the upstream hybrid
       # KV recovery fix lands: https://github.com/vllm-project/vllm/pull/45497
 
+# DeepSeek-V4-Pro FP4 AgentX on one MI355X node using ATOM MTP. Throughput
+# 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
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: cluster:mi355x-amds
+  precision: fp4
+  framework: atom
+  multinode: false
+  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] }
+
 dsr1-fp4-mi355x-sglang-disagg-mtp:
   image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260519
   model: amd/DeepSeek-R1-0528-MXFP4-v2
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 93b6a7c1b..b2a5962b5 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6196,6 +6196,18 @@
     - "Set max-num-seqs to twice the concurrency, select CUDA graph capture sizes by concurrency, and cap max-num-batched-tokens at 16384."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2576
 
+- config-keys:
+    - dsv4-fp4-mi355x-atom-agentic-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Add DeepSeek-V4-Pro FP4 ATOM MTP AgentX on one 8x MI355X node at concurrency 1, 2, 4, 8, 16, 32, and 48, with no KV offload and max-num-seqs set to twice concurrency."
+    - "Use rocm/atom-dev:nightly_202608201032, FP8 KV/index caches, prefix caching, 32K state checkpoints, 16K batching/prefill chunks, and FULL cudagraph mode."
+    - "Use three-token MTP with the committed DeepSeek-V4 thinking-mode golden AL 2.49 (synthetic acceptance length 3) for throughput, while eval-only runs measure real MTP acceptance."
+    - "Increase the AgentX warmup grace period from the 1800-second default to 3600 seconds at concurrency 32 and 48, matching the DeepSeek-V4-Pro SGLang saturation recipe so in-flight warmup requests can drain and reused long prefixes are fully primed before profiling."
+    - "Keep concurrency 1 through 16 at the default 1800 seconds; the profiling duration remains 3600 seconds for every concurrency arm."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2698
+
 - config-keys:
     - kimik3-fp4-b200-dynamo-vllm-agentic-dspark
   scenario-type: