diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index 72ef89c09..584fbcab9 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -186,7 +186,7 @@ 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: lmsysorg/sglang-rocm:v0.5.10rc0-rocm720-mi35x-20260330
   model: Qwen/Qwen3.5-397B-A17B-FP8
   model-prefix: qwen3.5
   runner: mi355x
@@ -197,11 +197,15 @@ qwen3.5-fp8-mi355x-sglang:
   - isl: 1024
     osl: 1024
     search-space:
-    - { tp: 8, conc-start: 4, conc-end: 64 }
+    - { tp: 2, conc-start: 8, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 32 }
+    - { tp: 8, conc-start: 4, conc-end: 4 }
   - isl: 8192
     osl: 1024
     search-space:
-    - { tp: 8, conc-start: 4, conc-end: 64 }
+    - { tp: 2, conc-start: 8, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 16 }
+    - { tp: 8, conc-start: 4, conc-end: 4 }
 
 qwen3.5-fp8-mi300x-sglang:
   image: lmsysorg/sglang:v0.5.9-rocm720-mi30x
diff --git a/benchmarks/single_node/qwen3.5_fp8_mi355x.sh b/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
old mode 100644
new mode 100755
index 701695def..6f5565784
--- a/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
+++ b/benchmarks/single_node/qwen3.5_fp8_mi355x.sh
@@ -19,29 +19,42 @@ hf download "$MODEL"
 
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
+MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
+CHUNK_SIZE=32768
 
 EVAL_CONTEXT_ARGS=""
-if [ "${EVAL_ONLY}" = "true" ]; then
-    setup_eval_context
-    EVAL_CONTEXT_ARGS="--context-length $EVAL_MAX_MODEL_LEN"
-fi
+#if [ "${EVAL_ONLY}" = "true" ]; then
+#    setup_eval_context
+#    EVAL_CONTEXT_ARGS="--context-length $EVAL_MAX_MODEL_LEN"
+#fi
 # 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 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
+    --mem-fraction-static $MEM_FRAC_STATIC \
+    --kv-cache-dtype fp8_e4m3 \
+    --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 \
+    $EVAL_CONTEXT_ARGS \
+    > $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" \
@@ -52,7 +65,8 @@ run_benchmark_serving \
     --num-prompts "$((CONC * 10))" \
     --max-concurrency "$CONC" \
     --result-filename "$RESULT_FILENAME" \
-    --result-dir /workspace/
+    --result-dir /workspace/ \
+    --trust-remote-code
 
 # After throughput, run evaluation only if RUN_EVAL is true
 if [ "${RUN_EVAL}" = "true" ]; then
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index a82882f61..5723d9801 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1235,3 +1235,10 @@
     - "New model support on ATOM framework"
     - "Kimi-K2.5 FP4, and MiniMax-M2.5 FP8 configs added for MI355X ATOM"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/963
+
+- config-keys:
+    - qwen3.5-fp8-mi355x-sglang
+  description:
+    - "Qwen3.5 fp8 mi355x performance update"
+    - "Relevant Issue: https://github.com/sgl-project/sglang/issues/19633"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/995