diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index 9e1f9834e..36f0eae97 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -411,6 +411,60 @@ kimik2.5-int4-mi300x-vllm:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
+kimik2.5-int4-mi355x-vllm-mtp:
+  image: vllm/vllm-openai-rocm:v0.19.0
+  model: moonshotai/Kimi-K2.5
+  model-prefix: kimik2.5
+  runner: mi355x
+  precision: int4
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64, spec-decoding: mtp }
+
+kimik2.5-int4-mi300x-vllm-mtp:
+  image: vllm/vllm-openai-rocm:v0.19.0
+  model: moonshotai/Kimi-K2.5
+  model-prefix: kimik2.5
+  runner: mi300x
+  precision: int4
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64, spec-decoding: mtp }
+
+kimik2.5-int4-mi325x-vllm-mtp:
+  image: vllm/vllm-openai-rocm:v0.19.0
+  model: moonshotai/Kimi-K2.5
+  model-prefix: kimik2.5
+  runner: mi325x
+  precision: int4
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, conc-start: 4, conc-end: 64, spec-decoding: mtp }
+    
 kimik2.5-fp4-mi355x-vllm:
   image: vllm/vllm-openai-rocm:v0.18.0
   model: amd/Kimi-K2.5-MXFP4
diff --git a/benchmarks/single_node/kimik2.5_int4_mi300x_mtp.sh b/benchmarks/single_node/kimik2.5_int4_mi300x_mtp.sh
new file mode 100644
index 000000000..6376b5be7
--- /dev/null
+++ b/benchmarks/single_node/kimik2.5_int4_mi300x_mtp.sh
@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    MAX_MODEL_LEN \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+# Set HIP_VISIBLE_DEVICES to match ROCR_VISIBLE_DEVICES for Ray compatibility in vLLM 0.14+
+if [ -n "$ROCR_VISIBLE_DEVICES" ]; then
+    export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
+fi
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    setup_eval_context
+    MAX_MODEL_LEN="$EVAL_MAX_MODEL_LEN"
+fi
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+echo "Ensuring host benchmark dependencies (aiohttp/transformers/numpy/tqdm/huggingface-hub/tiktoken)..."
+python3 -m pip install --no-cache-dir aiohttp transformers numpy tqdm huggingface-hub tiktoken
+
+
+
+set -x
+export VLLM_ROCM_USE_AITER=1
+export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
+export VLLM_ROCM_USE_AITER_RMSNORM=0
+export VLLM_SPEC_CONFIG="${VLLM_SPEC_CONFIG:-{\"model\": \"nvidia/Kimi-K2.5-Thinking-Eagle3\", \"method\": \"eagle3\", \"num_speculative_tokens\": 3}}"
+
+vllm serve $MODEL --port $PORT \
+--tensor-parallel-size=$TP \
+--gpu-memory-utilization 0.8 \
+--max-model-len $MAX_MODEL_LEN \
+--block-size=64 \
+--trust-remote-code \
+--no-enable-prefix-caching \
+--max-num-seqs 256 \
+--speculative-config "$VLLM_SPEC_CONFIG" \
+--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
+
+
diff --git a/benchmarks/single_node/kimik2.5_int4_mi325x_mtp.sh b/benchmarks/single_node/kimik2.5_int4_mi325x_mtp.sh
new file mode 100644
index 000000000..6376b5be7
--- /dev/null
+++ b/benchmarks/single_node/kimik2.5_int4_mi325x_mtp.sh
@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    MAX_MODEL_LEN \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+# Set HIP_VISIBLE_DEVICES to match ROCR_VISIBLE_DEVICES for Ray compatibility in vLLM 0.14+
+if [ -n "$ROCR_VISIBLE_DEVICES" ]; then
+    export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
+fi
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    setup_eval_context
+    MAX_MODEL_LEN="$EVAL_MAX_MODEL_LEN"
+fi
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+echo "Ensuring host benchmark dependencies (aiohttp/transformers/numpy/tqdm/huggingface-hub/tiktoken)..."
+python3 -m pip install --no-cache-dir aiohttp transformers numpy tqdm huggingface-hub tiktoken
+
+
+
+set -x
+export VLLM_ROCM_USE_AITER=1
+export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
+export VLLM_ROCM_USE_AITER_RMSNORM=0
+export VLLM_SPEC_CONFIG="${VLLM_SPEC_CONFIG:-{\"model\": \"nvidia/Kimi-K2.5-Thinking-Eagle3\", \"method\": \"eagle3\", \"num_speculative_tokens\": 3}}"
+
+vllm serve $MODEL --port $PORT \
+--tensor-parallel-size=$TP \
+--gpu-memory-utilization 0.8 \
+--max-model-len $MAX_MODEL_LEN \
+--block-size=64 \
+--trust-remote-code \
+--no-enable-prefix-caching \
+--max-num-seqs 256 \
+--speculative-config "$VLLM_SPEC_CONFIG" \
+--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
+
+
diff --git a/benchmarks/single_node/kimik2.5_int4_mi355x_mtp.sh b/benchmarks/single_node/kimik2.5_int4_mi355x_mtp.sh
new file mode 100644
index 000000000..6376b5be7
--- /dev/null
+++ b/benchmarks/single_node/kimik2.5_int4_mi355x_mtp.sh
@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    MAX_MODEL_LEN \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+# Set HIP_VISIBLE_DEVICES to match ROCR_VISIBLE_DEVICES for Ray compatibility in vLLM 0.14+
+if [ -n "$ROCR_VISIBLE_DEVICES" ]; then
+    export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
+fi
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+if [ "${EVAL_ONLY}" = "true" ]; then
+    setup_eval_context
+    MAX_MODEL_LEN="$EVAL_MAX_MODEL_LEN"
+fi
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+echo "Ensuring host benchmark dependencies (aiohttp/transformers/numpy/tqdm/huggingface-hub/tiktoken)..."
+python3 -m pip install --no-cache-dir aiohttp transformers numpy tqdm huggingface-hub tiktoken
+
+
+
+set -x
+export VLLM_ROCM_USE_AITER=1
+export VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=INT4
+export VLLM_ROCM_USE_AITER_RMSNORM=0
+export VLLM_SPEC_CONFIG="${VLLM_SPEC_CONFIG:-{\"model\": \"nvidia/Kimi-K2.5-Thinking-Eagle3\", \"method\": \"eagle3\", \"num_speculative_tokens\": 3}}"
+
+vllm serve $MODEL --port $PORT \
+--tensor-parallel-size=$TP \
+--gpu-memory-utilization 0.8 \
+--max-model-len $MAX_MODEL_LEN \
+--block-size=64 \
+--trust-remote-code \
+--no-enable-prefix-caching \
+--max-num-seqs 256 \
+--speculative-config "$VLLM_SPEC_CONFIG" \
+--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT"
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
+
+