diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
old mode 100644
new mode 100755
index 5551860f2..e4e82c16d
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -228,7 +228,7 @@ qwen3.5-fp8-mi325x-sglang:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
 qwen3.5-fp8-mi355x-sglang:
-  image: rocm/sgl-dev:v0.5.8.post1-rocm720-mi35x-20260218
+  image: rocm/sgl-dev:v0.5.9-rocm720-mi35x-20260315
   model: Qwen/Qwen3.5-397B-A17B-FP8
   model-prefix: qwen3.5
   runner: mi355x
diff --git a/benchmarks/single_node/qwen3.5_fp8_mi355x.sh b/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
index f77390707..70759d5fe 100644
--- a/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
+++ b/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
@@ -19,24 +19,37 @@ hf download "$MODEL"
 
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
+MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
+CHUNK_SIZE=8192
 
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
 
-python3 -m sglang.launch_server \
+set -x
+sglang serve \
     --attention-backend triton \
     --model-path $MODEL \
     --host=0.0.0.0 \
     --port $PORT \
     --tensor-parallel-size $TP \
     --trust-remote-code \
-    --mem-fraction-static 0.8 > $SERVER_LOG 2>&1 &
+    --mem-fraction-static $MEM_FRAC_STATIC \
+    --kv-cache-dtype fp8_e4m3 \
+    --mamba-ssm-dtype bfloat16 \
+    --cuda-graph-max-bs $CONC \
+    --max-running-requests $CONC \
+    --chunked-prefill-size $CHUNK_SIZE \
+    --max-prefill-tokens $CHUNK_SIZE \
+    --disable-radix-cache \
+    --num-continuous-decode-steps 2 \
+    --tokenizer-worker-num $TP \
+    > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
 
 # Wait for server to be ready
 wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
-
+export PYTHONDONTWRITEBYTECODE=1
 run_benchmark_serving \
     --model "$MODEL" \
     --port "$PORT" \
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
old mode 100644
new mode 100755
index 2090a1b25..c7182d4c7
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -961,3 +961,12 @@
   description:
     - "Extend MiniMax M2.5 FP8 single-node config for H200 with vLLM v0.16.0 (TP8)"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/869
+
+- config-keys:
+    - qwen3.5-fp8-mi355x-sglang
+  description:
+    - "Improved fp8 performance"
+    - "Relevant Issue: https://github.com/sgl-project/sglang/issues/19633"
+    - "Relevant PR: https://github.com/sgl-project/sglang/pull/19826"
+    - "Image: rocm/sgl-dev:v0.5.9-rocm720-mi35x-20260315"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/910