diff --git a/benchmarks/single_node/agentic/dsv4_fp4_mi355x_sglang_mtp.sh b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_sglang_mtp.sh
new file mode 100755
index 000000000..9d8dd2610
--- /dev/null
+++ b/benchmarks/single_node/agentic/dsv4_fp4_mi355x_sglang_mtp.sh
@@ -0,0 +1,217 @@
+#!/usr/bin/env bash
+set -eo pipefail
+set -x
+
+# Agentic trace replay benchmark for DeepSeek-V4-Pro FP4 on MI355X using SGLang.
+#
+# KV_OFFLOADING=dram requires KV_OFFLOAD_BACKEND=hicache.
+#
+# Required env vars:
+#   MODEL, TP, CONC, KV_OFFLOADING, TOTAL_CPU_DRAM_GB, RESULT_DIR
+#
+# KV_OFFLOADING=dram requires one of these.
+#   KV_OFFLOAD_BACKEND=hicache.
+
+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 $SLURMD_NODENAME"
+fi
+
+# ROCR/HIP visibility under slurm cgroups.
+if [ -n "$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="$MODEL"
+fi
+rocm-smi || true
+amd-smi || true
+
+# ---- Resolve traces and install deps ----------------------------------------
+resolve_trace_source
+install_agentic_deps
+
+# ---- Server config ----------------------------------------------------------
+SERVER_LOG="$RESULT_DIR/server.log"
+mkdir -p "$RESULT_DIR"
+
+CACHE_ARGS=()
+if agentic_kv_offload_enabled; then
+    # HiCache config — https://lmsysorg.mintlify.app/cookbook/autoregressive/DeepSeek/DeepSeek-V4
+    case "$KV_OFFLOAD_BACKEND" in
+        hicache)
+            HICACHE_RATIO=4
+            HICACHE_WRITE_POLICY="write_through"
+            HICACHE_IO_BACKEND="direct"
+            HICACHE_MEM_LAYOUT="page_first_direct"
+            CACHE_ARGS=(
+                --enable-hierarchical-cache
+                --hicache-ratio "$HICACHE_RATIO"
+                --hicache-write-policy "$HICACHE_WRITE_POLICY"
+                --hicache-io-backend "$HICACHE_IO_BACKEND"
+                --hicache-mem-layout "$HICACHE_MEM_LAYOUT"
+            )
+            echo "HiCache DSv4 CPU tier: ratio=$HICACHE_RATIO, write_policy=$HICACHE_WRITE_POLICY, io_backend=$HICACHE_IO_BACKEND, mem_layout=$HICACHE_MEM_LAYOUT"
+            ;;
+        *)
+            echo "Error: unsupported KV_OFFLOAD_BACKEND '$KV_OFFLOAD_BACKEND' (expected: hicache)" >&2
+            exit 1
+            ;;
+    esac
+fi
+# ---- Client config ----------------------------------------------------------
+export AIPERF_HTTP_TCP_USER_TIMEOUT=1000000
+
+# ---- LLM server config ----------------------------------------------------------
+USE_SGLANG_ROUTER=false
+SGLANG_BACKEND_PORT="$PORT"
+ROUTER_LOG="$RESULT_DIR/router.log"
+MEM_FRACTION_STATIC=0.90
+CHUNKED_PREFILL_SIZE=8192
+PARALLEL_ARGS=(--tensor-parallel-size "$TP")
+if [ "$DP_ATTENTION" = "true" ]; then
+    USE_SGLANG_ROUTER=true
+    export AIPERF_HTTP_X_SMG_ROUTING_KEY_FROM_CORRELATION_ID=true
+    SGLANG_BACKEND_PORT=$((PORT + 1))
+    SGLANG_ROUTER_METRICS_PORT=$((PORT + 10000))
+    SGLANG_ROUTER_CMD=(python3 -m sglang_router.launch_router)
+
+    export SGLANG_SHARED_EXPERT_TP1=1
+    export SGLANG_DP_SHARED_EXPERT_LOCAL=1
+    export SGLANG_DP_USE_GATHERV=1
+    export SGLANG_DP_USE_REDUCE_SCATTER=1
+    export GPU_MAX_HW_QUEUES=5
+
+    CHUNKED_PREFILL_SIZE=$((8192 * TP))
+    PARALLEL_ARGS+=(
+        --dp "$TP"
+        --enable-dp-attention
+        --enable-dp-attention-local-control-broadcast
+    )
+fi
+
+if [ "$EP_SIZE" -gt 1 ]; then
+    PARALLEL_ARGS+=(--ep-size "$EP_SIZE")
+fi
+# AgentX concurrency counts live session trees, not individual requests.
+# Allow subagent fan-out to exceed CONC without clipping request bursts.
+MAX_RUNNING_REQUESTS=$((2 * CONC))
+CUDA_GRAPH_MAX_BS=$CONC
+[ "$CUDA_GRAPH_MAX_BS" -gt 128 ] && CUDA_GRAPH_MAX_BS=128
+# Simulated acceptance-length (AL) settings.
+# openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "The   input (3620936 tokens) is longer than the model's context length (1048576       tokens).", 'type': 'BadRequestError', 'param': None, 'code': 400} 
+export SGLANG_DEFAULT_THINKING=1
+export SGLANG_DSV4_REASONING_EFFORT=high
+export SGLANG_SIMULATE_ACC_LEN=2.49
+export SGLANG_SIMULATE_ACC_METHOD=match-expected
+export SGLANG_SIMULATE_ACC_TOKEN_MODE=real-draft-token
+
+export SGLANG_USE_ROCM700A=0
+export SGLANG_HACK_FLASHMLA_BACKEND=unified_kv_triton
+export AITER_BF16_FP8_MOE_BOUND=0
+
+export SGLANG_ENABLE_UNIFIED_RADIX_TREE=1
+export SGLANG_OPT_UNIFIED_CACHE_FREE_OUT_OF_WINDOW_SLOTS=1
+
+METRICS_ARGS=(--enable-metrics)
+SPEC_ARGS=(
+    --speculative-algorithm EAGLE
+    --speculative-num-steps 3
+    --speculative-eagle-topk 1
+    --speculative-num-draft-tokens 4
+)
+
+SGLANG_CMD=(
+    python3 -m sglang.launch_server
+    --model-path "$MODEL_PATH"
+    --served-model-name "$MODEL"
+    --host 0.0.0.0
+    --port "$SGLANG_BACKEND_PORT"
+    --trust-remote-code
+    "${PARALLEL_ARGS[@]}"
+    --attention-backend compressed
+    --cuda-graph-max-bs-decode "$CUDA_GRAPH_MAX_BS"
+    --max-running-requests "$MAX_RUNNING_REQUESTS"
+    --mem-fraction-static "$MEM_FRACTION_STATIC"
+    --swa-full-tokens-ratio 0.10
+    --page-size 256
+    --kv-cache-dtype fp8_e4m3
+    --chunked-prefill-size "$CHUNKED_PREFILL_SIZE"
+    --disable-shared-experts-fusion
+    --tool-call-parser deepseekv4
+    --reasoning-parser deepseek-v4
+    --chat-template "$(dirname "$0")/../chat_templates/deepseek_v4_thinking.jinja"
+    --watchdog-timeout 1800
+    "${METRICS_ARGS[@]}"
+    "${SPEC_ARGS[@]}"
+    "${CACHE_ARGS[@]}"
+)
+
+printf '%q ' "${SGLANG_CMD[@]}" | tee "$RESULT_DIR/sglang_command.txt"
+printf '\n' | tee -a "$RESULT_DIR/sglang_command.txt"
+
+{
+    echo "=== SGLANG_* env vars at launch ==="
+    env | grep -E '^SGLANG_' | sort
+    echo "==================================="
+} | tee "$SERVER_LOG"
+
+echo "Starting SGLang server for MI355X..."
+"${SGLANG_CMD[@]}" >> "$SERVER_LOG" 2>&1 &
+SERVER_PID=$!
+echo "Server PID: $SERVER_PID"
+
+capture_cache_metrics() {
+    {
+        echo "=== SGLang cache metrics snapshot $(date --iso-8601=seconds) ==="
+        curl -fsS "http://localhost:$SGLANG_BACKEND_PORT/metrics" 2>/dev/null \
+            | grep -E '^(sglang:(cache_hit_rate|cached_tokens_total|prompt_tokens_total|hicache_host_used_tokens|hicache_host_total_tokens|token_usage|num_requests_running|num_requests_waiting))' \
+            || true
+        echo "============================================================"
+    } >> "$SERVER_LOG"
+}
+
+wait_for_server_ready --port "$SGLANG_BACKEND_PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+if [ "$USE_SGLANG_ROUTER" = "true" ]; then
+    echo "Starting SGLang router on port $PORT for $TP DP ranks..."
+    "${SGLANG_ROUTER_CMD[@]}" \
+        --worker-urls "http://localhost:$SGLANG_BACKEND_PORT" \
+        --policy consistent_hashing \
+        --request-id-headers x-correlation-id \
+        --dp-aware \
+        --host 0.0.0.0 \
+        --port "$PORT" \
+        --prometheus-host 127.0.0.1 \
+        --prometheus-port "$SGLANG_ROUTER_METRICS_PORT" \
+        --connect-timeout-secs 900 \
+        --request-timeout-secs 14400 \
+        --disable-health-check \
+        --disable-retries > "$ROUTER_LOG" 2>&1 &
+    ROUTER_PID=$!
+    echo "Router PID: $ROUTER_PID"
+    wait_for_server_ready --port "$PORT" --server-log "$ROUTER_LOG" --server-pid "$ROUTER_PID"
+fi
+# ---- Run benchmark ----------------------------------------------------------
+
+if [ "${#METRICS_ARGS[@]}" -gt 0 ]; then
+    capture_cache_metrics
+    trap capture_cache_metrics EXIT
+fi
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    run_eval --port "$PORT"
+else
+    build_replay_cmd "$RESULT_DIR"
+    REPLAY_CMD+=" --server-metrics http://localhost:$SGLANG_BACKEND_PORT/metrics"
+    run_agentic_replay_and_write_outputs "$RESULT_DIR"
+fi
diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml
index ebe0cb29d..33ef655f6 100644
--- a/configs/amd-master.yaml
+++ b/configs/amd-master.yaml
@@ -1568,6 +1568,20 @@ dsv4-fp4-mi355x-sglang-agentic-hicache:
       - { tp: 8, dp-attn: true, kv-offloading: none, conc-list: [16, 32, 48, 64] }
       - { tp: 8, dp-attn: true, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [64] }
 
+dsv4-fp4-mi355x-sglang-agentic-mtp:
+  image: lmsysorg/sglang-rocm:v0.5.15.post1-rocm720-mi35x-20260714
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: cluster:mi355x-amds
+  precision: fp4
+  framework: sglang
+  multinode: false
+  scenarios:
+    agentic-coding:
+    - dram-utilization: 0.80
+      search-space:
+      - { tp: 8, dp-attn: true, kv-offloading: none, conc-list: [4, 8, 16, 32], spec-decoding: mtp }
+
 # MiniMax-M3 MXFP8 MI355X recipe:
 # https://github.com/vllm-project/recipes/commit/2a3728ed9892debfd767a72a58ebc90b33f186e5
 # MXFP8 runs from TP=4 on gfx950; block size 128 is mandatory for MSA.
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 75f85985c..85b83f84f 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4986,6 +4986,12 @@
     - "HiCache spills evicted prefixes to host DRAM and restores them at C2C bandwidth instead of recomputing; sizing follows the qwen3.5-fp8-b300-sglang-agentic-hicache recipe (GLM-5.2 is plain GQA: one host pool per rank, GB-based --hicache-size)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2280
 
+- config-keys:
+    - dsv4-fp4-mi355x-sglang-agentic-mtp
+  description:
+    - "Add DSv4 FP4 MI355X SGLang agentic MTP recipe (separate from hicache config)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2254
+
 - config-keys:
     - glm5.2-fp4-b300-sglang-agentic
   description:
@@ -5013,7 +5019,6 @@
     - "LMCache MP server (lmcache_driven transfer mode) + LMCacheMPConnector per PR #2153/#2231; L1 pool derated to 75% of TOTAL_CPU_DRAM_GB; PYTORCH_ALLOC_CONF=expandable_segments:True dropped on the lmcache arms only (VMM allocations cannot be CUDA-IPC-exported to the LMCache server, same failure mode as cuMem on B200); gpu-memory-utilization 0.92 on lmcache DEP8 (matches the official DEP8 derate) and 0.94 on lmcache TP4/DEP4 (at 0.96 the PR #2232 bring-up sweeps hit torch-pool, DeepGEMM-JIT, and cuBLAS-workspace OOMs; 23 lmcache points validated green in runs 29463061871/29535333851 after the derate)"
     - "LMCache ladders offset the official arms: TP4 +4 conc [32, 36, 40, 44] vs SimpleCPU [28, 32, 36, 40]; DEP4 +4 conc [36, 44, 52, 60, 68, 76] vs SimpleCPU [32, 40, 48, 56, 64, 72]; DEP8 +8 conc capped at 208 [72, 104, 120, 136, 152, 168, 184, 200] vs GPU-resident [64, 96, 112, 128, 144, 160, 176, 192, 224]"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2232
-  
 
 - config-keys:
     - dsv4-fp4-b200-vllm-agentic
diff --git a/runners/launch_mi355x-amds.sh b/runners/launch_mi355x-amds.sh
index 75a67c1c5..4cdc314a0 100644
--- a/runners/launch_mi355x-amds.sh
+++ b/runners/launch_mi355x-amds.sh
@@ -268,7 +268,7 @@ else
     export GPU_COUNT="${GPU_COUNT:-${TP:?TP must be set}}"
 
     set -x
-    salloc --partition=$PARTITION --gres=gpu:$GPU_COUNT --exclusive --cpus-per-task=128 --time=500 --no-shell --job-name="$RUNNER_NAME"
+    salloc --partition=$PARTITION --gres=gpu:$GPU_COUNT --exclusive --cpus-per-task=128 --time=500 --no-shell --job-name="$RUNNER_NAME" --exclude=mia1-p01-g09,mia1-p01-g11
     JOB_ID=$(squeue --name="$RUNNER_NAME" -h -o %A | head -n1)
 
     srun --jobid=$JOB_ID bash -c "docker stop \$(docker ps -a -q)"