diff --git a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
index 87809f54b6..eb23d38b1a 100644
--- a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
+++ b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
@@ -21,6 +21,7 @@ export SGLANG_USE_AITER=1
 export SGLANG_USE_AITER_UNIFIED_ATTN=1
 export AITER_FLYDSL_FORCE=1
 export SGLANG_MAMBA_SSM_DTYPE=bfloat16
+export ROCM_QUICK_REDUCE_QUANTIZATION=INT8
 
 SERVER_LOG=/workspace/server.log
 MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
@@ -41,7 +42,7 @@ python3 -m sglang.launch_server --model-path=$MODEL --trust-remote-code \
 --model-loader-extra-config '{"enable_multithread_load": true}' \
 --watchdog-timeout 1200  \
 --disable-radix-cache \
---enable-aiter-allreduce-fusion --max-running-requests $CONC \
+--max-running-requests $CONC \
 --page-size 16 \
 > $SERVER_LOG 2>&1 &
 
diff --git a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
index 16e86e5443..6488d1380c 100755
--- a/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
+++ b/benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
@@ -21,6 +21,7 @@ export SGLANG_USE_AITER=1
 export SGLANG_USE_AITER_UNIFIED_ATTN=1
 export AITER_FLYDSL_FORCE=1
 export SGLANG_MAMBA_SSM_DTYPE=bfloat16
+export ROCM_QUICK_REDUCE_QUANTIZATION=INT8
 
 SERVER_LOG=/workspace/server.log
 MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
@@ -41,7 +42,7 @@ python3 -m sglang.launch_server --model-path=$MODEL --trust-remote-code \
 --model-loader-extra-config '{"enable_multithread_load": true}' \
 --watchdog-timeout 1200  \
 --disable-radix-cache \
---enable-aiter-allreduce-fusion --max-running-requests $CONC \
+--max-running-requests $CONC \
 --page-size 16 \
 --speculative-algorithm EAGLE \
 --speculative-num-steps 3 \
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index b358f10bf1..4e75e3682c 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -4887,6 +4887,14 @@
     - "Add SGLANG_MAMBA_SSM_DTYPE=bfloat16 in both non-MTP and MTP benchmark scripts"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2201  
 
+- config-keys:
+    - qwen3.5-fp4-mi355x-sglang
+    - qwen3.5-fp4-mi355x-sglang-mtp
+  description:
+    - "Add ROCM_QUICK_REDUCE_QUANTIZATION=INT8 in both non-MTP and MTP benchmark scripts"
+    - "Remove --enable-aiter-allreduce-fusion from both non-MTP and MTP launch commands"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2265
+
 - config-keys:
     - dsv4-fp4-b200-vllm-agentic
   description: