diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index 3cbd9c49c..64c48477f 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2065,7 +2065,7 @@ qwen3.5-fp4-b200-sglang:
       - { tp: 2, ep: 1, conc-start: 4, conc-end: 128 }
 
 qwen3.5-fp4-b200-sglang-mtp:
-  image: lmsysorg/sglang:nightly-dev-20260402-d7256eb6
+  image: lmsysorg/sglang:nightly-dev-20260422-de962f32
   model: nvidia/Qwen3.5-397B-A17B-NVFP4
   model-prefix: qwen3.5
   runner: b200
@@ -2077,11 +2077,13 @@ qwen3.5-fp4-b200-sglang-mtp:
     - isl: 1024
       osl: 1024
       search-space:
-      - { tp: 4, ep: 1, conc-start: 4, conc-end: 128, spec-decoding: mtp }
+      - { tp: 4, ep: 1, conc-start: 4, conc-end: 4, spec-decoding: mtp }
+      - { tp: 2, ep: 1, conc-start: 4, conc-end: 64, spec-decoding: mtp }
     - isl: 8192
       osl: 1024
       search-space:
-      - { tp: 4, ep: 1, conc-start: 4, conc-end: 128, spec-decoding: mtp }
+      - { tp: 4, ep: 1, conc-start: 4, conc-end: 4, spec-decoding: mtp }
+      - { tp: 2, ep: 1, conc-start: 4, conc-end: 64, spec-decoding: mtp }
 
 glm5-fp8-b200-sglang:
   image: lmsysorg/sglang:nightly-dev-cu13-20260317-1eea7448
diff --git a/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh b/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh
index 72e2f9c39..961e3b710 100755
--- a/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh
+++ b/benchmarks/single_node/qwen3.5_fp4_b200_mtp.sh
@@ -20,61 +20,43 @@ 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 [[ $CONC -ge 16 ]]; then
-  SCHEDULER_RECV_INTERVAL=30
-else
-  SCHEDULER_RECV_INTERVAL=10
-fi
-
-MEM_FRAC_STATIC=0.85
-CHUNKED_PREFILL_SIZE=32768
-MAX_PREFILL_TOKENS=32768
-CUDA_GRAPH_MAX_BATCH_SIZE=$CONC
-MAX_RUNNING_REQUESTS=128
 CONTEXT_LENGTH=$((ISL + OSL + 20))
 if [ "${EVAL_ONLY}" = "true" ]; then
     setup_eval_context
     CONTEXT_LENGTH="$EVAL_MAX_MODEL_LEN"
 fi
 
-if [[ $TP -eq 8 ]]; then
-  EXTRA_ARGS="--enable-flashinfer-allreduce-fusion"
-else
-  EXTRA_ARGS=""
-fi
-
-echo "SCHEDULER_RECV_INTERVAL: $SCHEDULER_RECV_INTERVAL, CONC: $CONC, ISL: $ISL, OSL: $OSL"
-
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
 
 set -x
-PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.0.0.0 --port=$PORT \
+SGLANG_ENABLE_SPEC_V2=1 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 $EP_SIZE \
---quantization modelopt_fp4 --fp4-gemm-backend flashinfer_cutlass \
+--tensor-parallel-size=$TP --data-parallel-size=1 --expert-parallel-size=$EP_SIZE \
+--enable-symm-mem \
+--disable-radix-cache \
+--quantization modelopt_fp4 \
 --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 $CONTEXT_LENGTH --disable-radix-cache \
---attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
-$EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
---tokenizer-worker-num 6 --stream-interval 30 \
+--attention-backend trtllm_mha \
+--moe-runner-backend flashinfer_trtllm \
+--cuda-graph-max-bs $CONC \
+--max-running-requests $CONC \
+--max-prefill-tokens 16384 \
+--chunked-prefill-size 16384 \
+--mem-fraction-static 0.8 \
+--stream-interval 50 \
+--scheduler-recv-interval $( [[ $CONC -gt 4 ]] && echo 30 || echo 10 ) \
+--tokenizer-worker-num 6 \
+--tokenizer-path $MODEL \
 --speculative-algorithm EAGLE \
 --speculative-num-steps 3 \
 --speculative-eagle-topk 1 \
 --speculative-num-draft-tokens 4 \
-> $SERVER_LOG 2>&1 &
+--context-length $CONTEXT_LENGTH > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
 
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 98002a100..d34b93dba 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -2221,3 +2221,13 @@
     - "Update the TensorRT-LLM DeepSeek-V4-Pro image to ghcr.io/semianalysisai/trtllm-deepseek-v4:feat-deepseek_v4-9aa3715"
     - "Enable TRTLLM fused MHC by default with the DeepSeek-V4 feature image"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1270
+
+- config-keys:
+    - qwen3.5-fp4-b200-sglang-mtp
+  description:
+    - "Update image to lmsysorg/sglang:nightly-dev-20260422-de962f32"
+    - "Add tp:2 ep:1 conc 4-128 search-space for 1k1k and 8k1k"
+    - "Align server flags with FP4 B200 STP: --enable-symm-mem, --expert-parallel-size, dynamic scheduler-recv-interval"
+    - "Add MTP flags: SGLANG_ENABLE_SPEC_V2=1, EAGLE speculative decoding (steps=3, topk=1, draft=4)"
+    - "Reduce prefill/chunked from 32768 to 16384"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1257