diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index fc837704c..52b80fae7 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1829,6 +1829,72 @@ qwen3.5-fp8-b200-sglang:
     - { tp: 8, ep: 1, conc-start: 4, conc-end: 4}
     - { tp: 4, ep: 4, conc-start: 8, conc-end: 64 }
 
+qwen3.5-bf16-b200-sglang-mtp:
+  image: lmsysorg/sglang:v0.5.9-cu130
+  model: Qwen/Qwen3.5-397B-A17B
+  model-prefix: qwen3.5
+  runner: b200
+  precision: bf16
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 8, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+
+qwen3.5-fp8-b200-sglang-mtp:
+  image: lmsysorg/sglang:v0.5.9-cu130
+  model: Qwen/Qwen3.5-397B-A17B-FP8
+  model-prefix: qwen3.5
+  runner: b200
+  precision: fp8
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+
+qwen3.5-fp4-b200-sglang-mtp:
+  image: lmsysorg/sglang:v0.5.9-cu130
+  model: nvidia/Qwen3.5-397B-A17B-NVFP4
+  model-prefix: qwen3.5
+  runner: b200
+  precision: fp4
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 1, conc-start: 4, conc-end: 512, spec-decoding: mtp }
+
 kimik2.5-int4-b200-vllm:
   image: vllm/vllm-openai:v0.15.1
   model: moonshotai/Kimi-K2.5
diff --git a/benchmarks/single_node/qwen3.5_bf16_b200_mtp.sh b/benchmarks/single_node/qwen3.5_bf16_b200_mtp.sh
new file mode 100644
index 000000000..3c6ecb73f
--- /dev/null
+++ b/benchmarks/single_node/qwen3.5_bf16_b200_mtp.sh
@@ -0,0 +1,90 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+nvidia-smi
+
+hf download "$MODEL"
+
+export NCCL_NVLS_ENABLE=1
+export SGL_ENABLE_JIT_DEEPGEMM=false
+export SGLANG_ENABLE_FLASHINFER_GEMM=true
+export PYTHONUNBUFFERED=1
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# Default: recv every ~10 requests; if CONC >= 16, relax to ~30 requests between scheduler recv polls.
+if [[ $CONC -ge 16 ]]; then
+  SCHEDULER_RECV_INTERVAL=30
+else
+  SCHEDULER_RECV_INTERVAL=10
+fi
+
+MEM_FRAC_STATIC=0.8
+CHUNKED_PREFILL_SIZE=32768
+MAX_PREFILL_TOKENS=32768
+CUDA_GRAPH_MAX_BATCH_SIZE=$CONC
+MAX_RUNNING_REQUESTS=128
+CONTEXT_LENGTH=$((ISL + OSL + 20))
+
+# MTP (Multi-Token Prediction) Config - EAGLE speculative decoding
+SPECULATIVE_NUM_STEPS=3
+SPECULATIVE_DRAFT_TOKENS=4
+SPECULATIVE_EAGLE_TOPK=1
+
+echo "SCHEDULER_RECV_INTERVAL: $SCHEDULER_RECV_INTERVAL, CONC: $CONC, ISL: $ISL, OSL: $OSL"
+
+set -x
+PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.0.0.0 --port=$PORT \
+--trust-remote-code \
+--tensor-parallel-size=$TP --data-parallel-size=1 --ep-size $EP_SIZE \
+--cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
+--mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
+--context-length $CONTEXT_LENGTH --disable-radix-cache \
+--attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+--enable-flashinfer-allreduce-fusion --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
+--tokenizer-worker-num 6 --stream-interval 30 \
+--speculative-algorithm EAGLE --speculative-num-steps $SPECULATIVE_NUM_STEPS --speculative-eagle-topk $SPECULATIVE_EAGLE_TOPK --speculative-num-draft-tokens $SPECULATIVE_DRAFT_TOKENS \
+> $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+pip install -q datasets pandas
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --use-chat-template
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+set +x
diff --git a/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh b/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh
new file mode 100644
index 000000000..48db1d66d
--- /dev/null
+++ b/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh
@@ -0,0 +1,90 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+nvidia-smi
+
+hf download "$MODEL"
+
+export NCCL_NVLS_ENABLE=1
+export SGL_ENABLE_JIT_DEEPGEMM=false
+export SGLANG_ENABLE_FLASHINFER_GEMM=true
+export PYTHONUNBUFFERED=1
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# Default: recv every ~10 requests; if CONC >= 16, relax to ~30 requests between scheduler recv polls.
+if [[ $CONC -ge 16 ]]; then
+  SCHEDULER_RECV_INTERVAL=30
+else
+  SCHEDULER_RECV_INTERVAL=10
+fi
+
+MEM_FRAC_STATIC=0.8
+CHUNKED_PREFILL_SIZE=32768
+MAX_PREFILL_TOKENS=32768
+CUDA_GRAPH_MAX_BATCH_SIZE=$CONC
+MAX_RUNNING_REQUESTS=128
+CONTEXT_LENGTH=$((ISL + OSL + 20))
+
+# MTP (Multi-Token Prediction) Config - EAGLE speculative decoding
+SPECULATIVE_NUM_STEPS=3
+SPECULATIVE_DRAFT_TOKENS=4
+SPECULATIVE_EAGLE_TOPK=1
+
+echo "SCHEDULER_RECV_INTERVAL: $SCHEDULER_RECV_INTERVAL, CONC: $CONC, ISL: $ISL, OSL: $OSL"
+
+set -x
+PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.0.0.0 --port=$PORT \
+--trust-remote-code \
+--tensor-parallel-size=$TP --data-parallel-size=1 --ep-size $EP_SIZE \
+--cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
+--mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
+--context-length $CONTEXT_LENGTH --disable-radix-cache \
+--attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm --fp4-gemm-backend flashinfer_cutlass --kv-cache-dtype fp8_e4m3 \
+--enable-flashinfer-allreduce-fusion --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
+--tokenizer-worker-num 6 --stream-interval 30 \
+--speculative-algorithm EAGLE --speculative-num-steps $SPECULATIVE_NUM_STEPS --speculative-eagle-topk $SPECULATIVE_EAGLE_TOPK --speculative-num-draft-tokens $SPECULATIVE_DRAFT_TOKENS \
+> $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+pip install -q datasets pandas
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --use-chat-template
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+set +x
diff --git a/benchmarks/single_node/qwen3.5_fp8_b200_mtp.sh b/benchmarks/single_node/qwen3.5_fp8_b200_mtp.sh
new file mode 100644
index 000000000..c8aa7490f
--- /dev/null
+++ b/benchmarks/single_node/qwen3.5_fp8_b200_mtp.sh
@@ -0,0 +1,91 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME \
+    EP_SIZE
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+nvidia-smi
+
+hf download "$MODEL"
+
+export NCCL_NVLS_ENABLE=1
+export SGL_ENABLE_JIT_DEEPGEMM=false
+export SGLANG_ENABLE_FLASHINFER_GEMM=true
+export PYTHONUNBUFFERED=1
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# Default: recv every ~10 requests; if CONC >= 16, relax to ~30 requests between scheduler recv polls.
+if [[ $CONC -ge 16 ]]; then
+  SCHEDULER_RECV_INTERVAL=30
+else
+  SCHEDULER_RECV_INTERVAL=10
+fi
+
+MEM_FRAC_STATIC=0.8
+CHUNKED_PREFILL_SIZE=32768
+MAX_PREFILL_TOKENS=32768
+CUDA_GRAPH_MAX_BATCH_SIZE=$CONC
+MAX_RUNNING_REQUESTS=128
+CONTEXT_LENGTH=$((ISL + OSL + 20))
+
+# MTP (Multi-Token Prediction) Config - EAGLE speculative decoding
+SPECULATIVE_NUM_STEPS=3
+SPECULATIVE_DRAFT_TOKENS=4
+SPECULATIVE_EAGLE_TOPK=1
+
+echo "SCHEDULER_RECV_INTERVAL: $SCHEDULER_RECV_INTERVAL, CONC: $CONC, ISL: $ISL, OSL: $OSL"
+
+set -x
+PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.0.0.0 --port=$PORT \
+--trust-remote-code \
+--tensor-parallel-size=$TP --data-parallel-size=1 --ep-size $EP_SIZE \
+--quantization fp8 --kv-cache-dtype fp8_e4m3 --mamba-ssm-dtype bfloat16 \
+--cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
+--mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
+--context-length $CONTEXT_LENGTH --disable-radix-cache \
+--attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+--enable-flashinfer-allreduce-fusion --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
+--tokenizer-worker-num 6 --stream-interval 30 \
+--speculative-algorithm EAGLE --speculative-num-steps $SPECULATIVE_NUM_STEPS --speculative-eagle-topk $SPECULATIVE_EAGLE_TOPK --speculative-num-draft-tokens $SPECULATIVE_DRAFT_TOKENS \
+> $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+pip install -q datasets pandas
+
+run_benchmark_serving \
+    --model "$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 "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --use-chat-template
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index c19ddbd1a..e86c630c3 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -931,4 +931,14 @@
     - "Switch to --attention-backend ROCM_AITER_UNIFIED_ATTN and add fuse_rope_kvcache compilation pass"
     - "Remove deprecated VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION/VLLM_ROCM_USE_AITER_MHA env vars and compilation-config cudagraph_mode"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/867
-  
+
+- config-keys:
+    - qwen3.5-bf16-b200-sglang-mtp
+    - qwen3.5-fp8-b200-sglang-mtp
+    - qwen3.5-fp4-b200-sglang-mtp
+  description:
+    - "Add Single Node Agg MTP configs for Qwen3.5 B200 SGLang (bf16, fp8, fp4)"
+    - "EAGLE speculative decoding: num-steps 3, draft-tokens 4, topk 1"
+    - "New scripts: benchmarks/single_node/qwen3.5_bf16_b200_mtp.sh, qwen3.5_fp8_b200_mtp.sh, qwen3.5_fp4_b200_mtp.sh"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/897
+