diff --git a/benchmarks/single_node/qwen3.5_bf16_mi355x.sh b/benchmarks/single_node/qwen3.5_bf16_mi355x.sh
index f77390707..e339c9658 100755
--- a/benchmarks/single_node/qwen3.5_bf16_mi355x.sh
+++ b/benchmarks/single_node/qwen3.5_bf16_mi355x.sh
@@ -19,6 +19,8 @@ hf download "$MODEL"
 
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
+CONTEXT_LENGTH=$((ISL + OSL + 20))
+MAX_PREFILL_TOKENS=32768
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
@@ -30,6 +32,13 @@ python3 -m sglang.launch_server \
     --port $PORT \
     --tensor-parallel-size $TP \
     --trust-remote-code \
+    --tokenizer-worker-num 6 \
+    --enable-torch-compile \
+    --cuda-graph-max-bs $CONC \
+    --context-length $CONTEXT_LENGTH \
+    --disable-radix-cache \
+    --max-prefill-tokens $MAX_PREFILL_TOKENS \
+    --scheduler-recv-interval 30 \
     --mem-fraction-static 0.8 > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/benchmarks/single_node/qwen3.5_fp8_mi355x.sh b/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
index f77390707..e339c9658 100644
--- a/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
+++ b/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
@@ -19,6 +19,8 @@ hf download "$MODEL"
 
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
+CONTEXT_LENGTH=$((ISL + OSL + 20))
+MAX_PREFILL_TOKENS=32768
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
@@ -30,6 +32,13 @@ python3 -m sglang.launch_server \
     --port $PORT \
     --tensor-parallel-size $TP \
     --trust-remote-code \
+    --tokenizer-worker-num 6 \
+    --enable-torch-compile \
+    --cuda-graph-max-bs $CONC \
+    --context-length $CONTEXT_LENGTH \
+    --disable-radix-cache \
+    --max-prefill-tokens $MAX_PREFILL_TOKENS \
+    --scheduler-recv-interval 30 \
     --mem-fraction-static 0.8 > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 1a19fd6a5..b7db494db 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1055,3 +1055,10 @@
     - "Enable VLLM_USE_FLASHINFER_MOE_INT4=1 for Kimi K2.5 INT4 B200 benchmark"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/935
 
+- config-keys:
+    - qwen3.5-fp8-mi355x-sglang
+    - qwen3.5-bf16-mi355x-sglang
+  description:
+    - "Update cli args of Qwen3.5 FP8 and BF16 SGLang benchmarks for MI355X to achieve better performance"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/942
+