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 100644
index 000000000..9016d651f
--- /dev/null
+++ b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_atom_mtp.sh
@@ -0,0 +1,120 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set -x
+
+# Agentic trace replay benchmark for DeepSeek-V4-Pro FP4 on MI355X using ATOM.
+#
+# Serving flags follow the validated MI355X recipe from
+# https://github.com/ROCm/ATOM/blob/main/recipes/DeepSeek-V4-Agentic-Benchmark.md
+# Image is configured in amd-master.yaml.
+#
+# Required env vars:
+#   MODEL, TP, CONC, KV_OFFLOADING, TOTAL_CPU_DRAM_GB, RESULT_DIR
+#
+# KV_OFFLOADING=dram is not enabled. 
+
+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 ${SLURMD_NODENAME:-unknown}"
+fi
+
+# `hf download` creates the target dir if missing and is itself idempotent.
+# When MODEL_PATH is unset (stand-alone runs), fall back to the HF_HUB_CACHE
+# Either way, MODEL_PATH is what the server is launched with.
+if [[ -n "${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="$MODEL"
+fi
+
+if [ -n "${ROCR_VISIBLE_DEVICES:-}" ]; then
+    export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
+fi
+
+# ---- Resolve traces and install deps ----------------------------------------
+resolve_trace_source
+install_agentic_deps
+
+# Nightly ROCm image may be missing runtime deps; ensure they are present.
+agentic_pip_install --quiet Pillow fastapi uvicorn
+
+export AIPERF_HTTP_TCP_USER_TIMEOUT=900000
+
+# DeepSeek-V4-Pro weights are large; engine startup can exceed default 600s.
+export VLLM_ENGINE_READY_TIMEOUT_S=3600
+
+# vllm-project/vllm#43447 keeps local SWA prefix-cache tails sparsely, while
+# vllm-project/vllm#44774 applies the same reachability policy to Mooncake's
+# store mask. 32k matches the trace-replay tuning validated for this workload.
+export VLLM_PREFIX_CACHE_RETENTION_INTERVAL=32768
+
+# VLLM_PREFIX_CACHE_RETENTION_INTERVAL only applies to sliding-window/Mamba
+# models; this vLLM build raises ValueError if it is set for DSv4.
+
+# ---- LLM server config ----------------------------------------------------------
+SERVER_LOG="$RESULT_DIR/server.log"
+VLLM_BACKEND_PORT="$PORT"
+mkdir -p "$RESULT_DIR"
+
+SERVER_PID=""
+ROUTER_PID=""
+MOONCAKE_MASTER_PID=""
+
+PARALLEL_ARGS=(-tp "$TP")
+SPEC_ARGS=(--method mtp --num-speculative-tokens 3 )
+OFFLOAD_ARGS=()
+if [ "$DP_ATTENTION" = "true" ]; then
+    PARALLEL_ARGS=(-tp "$TP" --enable-dp-attention)
+fi
+if [ "$EP_SIZE" -gt 1 ]; then
+    PARALLEL_ARGS+=(--enable-expert-parallel)
+fi
+
+# AgentX concurrency counts live session trees, not individual requests.
+# Subagent fan-out can push instantaneous request concurrency above CONC, so
+# leave 2x headroom rather than clipping those bursts at the scheduler.
+MAX_NUM_SEQS=$((2 * CONC))
+
+echo "Starting atom server..."
+set -x
+export AITER_BF16_FP8_MOE_BOUND=0
+export ATOM_MOE_GU_ITLV=1
+export AITER_LOG_LEVEL=WARNING
+export ATOM_DISABLE_MMAP=true
+export MEM_FRAC_STATIC=0.9
+
+{ set +x; } 2>/dev/null
+ATOM_CMD=(
+    python3 -m atom.entrypoints.openai_server
+    --model "$MODEL_PATH" 
+    --server-port "$VLLM_BACKEND_PORT"
+    "${PARALLEL_ARGS[@]}"
+    "${SPEC_ARGS[@]}"
+    --kv_cache_dtype fp8
+    --trust-remote-code 
+    --enable_prefix_caching
+    --max-num-seqs "$MAX_NUM_SEQS"
+    --gpu-memory-utilization "$MEM_FRAC_STATIC"
+    "${OFFLOAD_ARGS[@]}"
+)
+
+printf '%q ' "${ATOM_CMD[@]}" | tee "$RESULT_DIR/atom_command.txt"
+printf '\n' | tee -a "$RESULT_DIR/atom_command.txt"
+"${ATOM_CMD[@]}" > "$SERVER_LOG" 2>&1 &
+SERVER_PID=$!
+echo "Server PID: $SERVER_PID"
+
+wait_for_server_ready --port "$VLLM_BACKEND_PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    run_eval --port "$PORT"
+else
+    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 0f547cba8..7f093fc09 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1356,6 +1356,20 @@ dsv4-fp4-mi355x-atom-mtp:
       search-space:
       - { tp: 8, ep: 1, conc-start: 1, conc-end: 1024, spec-decoding: mtp }
 
+dsv4-fp4-mi355x-atom-agentic-mtp:
+  image: rocm/atom-dev:nightly_202607211523
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: cluster:mi355x-amds
+  precision: fp4
+  framework: atom
+  multinode: false
+  scenarios:
+    agentic-coding:
+    - dram-utilization: 0.60
+      search-space:
+      - { tp: 8, ep: 1, dp-attn: false, kv-offloading: none, conc-list: [1, 2, 4, 8, 16, 32, 48], spec-decoding: mtp }
+
 qwen3.5-bf16-mi325x-sglang-mtp:
   image: lmsysorg/sglang:v0.5.12-rocm720-mi30x
   model: Qwen/Qwen3.5-397B-A17B
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index c3602ff74..e8517f5bf 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -5085,3 +5085,10 @@
   description:
     - "Bump SGLang container image from lmsysorg/sglang:v0.5.12-cu130 to lmsysorg/sglang:v0.5.15.post1-cu130 (https://github.com/sgl-project/sglang/releases/tag/v0.5.15.post1)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2313
+
+- config-keys:
+    - dsv4-fp4-mi355x-atom-agentic-mtp
+  description:
+    - "Add DeepSeek-V4-Pro FP4 MI355X ATOM agentic-coding MTP benchmark serving via the ATOM openai_server entrypoint with speculative decoding (--method mtp --num-speculative-tokens 3), following the ROCm ATOM DeepSeek-V4-Agentic recipe (https://github.com/ROCm/ATOM/blob/main/recipes/DeepSeek-V4-Agentic-Benchmark.md)"
+    - "Register the dsv4-fp4-mi355x-atom-agentic-mtp config in configs/amd-master.yaml on rocm/atom-dev:nightly_202607211523 (TP8/EP1, conc list [1,2,4,8,16,32,48], spec-decoding mtp, no KV offload)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2346