diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index b35716e78..d483007bf 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -226,6 +226,26 @@ qwen3.5-fp4-mi355x-sglang:
     - { tp: 2, conc-start: 4, conc-end: 256 }
     - { tp: 4, conc-start: 4, conc-end: 16 }
 
+qwen3.5-fp4-mi355x-sglang-mtp:
+  image: lmsysorg/sglang-rocm:v0.5.10rc0-rocm700-mi35x-20260417
+  model: amd/Qwen3.5-397B-A17B-MXFP4
+  model-prefix: qwen3.5
+  runner: mi355x
+  precision: fp4
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 2, conc-start: 4, conc-end: 256, spec-decoding: mtp }
+    - { tp: 4, conc-start: 4, conc-end: 16, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 2, conc-start: 4, conc-end: 256, spec-decoding: mtp }
+    - { tp: 4, conc-start: 4, conc-end: 16, spec-decoding: mtp }
+
 qwen3.5-fp8-mi300x-sglang:
   image: lmsysorg/sglang:v0.5.10-rocm720-mi30x
   model: Qwen/Qwen3.5-397B-A17B-FP8
diff --git a/benchmarks/single_node/qwen3.5_fp4_mi355x_mtp.sh b/benchmarks/single_node/qwen3.5_fp4_mi355x_mtp.sh
new file mode 100755
index 000000000..5f00e68dc
--- /dev/null
+++ b/benchmarks/single_node/qwen3.5_fp4_mi355x_mtp.sh
@@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+export SGLANG_USE_AITER=1
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    setup_eval_context
+fi
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+python3 -m sglang.launch_server --model-path=$MODEL --trust-remote-code \
+--host=0.0.0.0 --port=$PORT \
+--tensor-parallel-size=$TP \
+--attention-backend aiter \
+--mem-fraction-static $MEM_FRAC_STATIC \
+--model-loader-extra-config '{"enable_multithread_load": true}' \
+--watchdog-timeout 1200  \
+--disable-radix-cache \
+--speculative-algorithm EAGLE \
+--speculative-num-steps 3 \
+--speculative-eagle-topk 1 \
+--speculative-num-draft-tokens 4 \
+> $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID" --sleep-interval 60
+
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts "$((CONC * 10))" \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 299540dbf..26ad27815 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1475,3 +1475,13 @@
     - "Expand GPT-OSS 120B FP4 MI300X TP=1 concurrency from 64 to 256 for 1k1k"
     - "Higher concurrency improves MoE weight amortization: 8552 total TPS at conc=256 vs 4016 at conc=64 (2.1x)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1053
+
+- config-keys:
+    - qwen3.5-fp4-mi355x-sglang-mtp
+  description:
+    - "Add Qwen3.5-397B-A17B MXFP4 MI355X SGLang MTP benchmark"
+    - "Image: lmsysorg/sglang-rocm:v0.5.10rc0-rocm700-mi35x-20260417"
+    - "Model: amd/Qwen3.5-397B-A17B-MXFP4"
+    - "Mirrors the qwen3.5-fp4-mi355x-sglang non-MTP recipe and adds EAGLE speculative decoding (num-steps=3, eagle-topk=1, num-draft-tokens=4)"
+    - "Configs: 1k1k and 8k1k, TP=2 conc 4-256 and TP=4 conc 4-16 with spec-decoding=mtp"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXXX