diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index a2674153a..a61f4fdd3 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -1,5 +1,5 @@
 dsr1-fp4-mi355x-sglang:
-  image: rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915
+  image: lmsysorg/sglang:v0.5.6.post1-rocm700-mi35x
   model: amd/DeepSeek-R1-0528-MXFP4-Preview
   model-prefix: dsr1
   runner: mi355x
diff --git a/benchmarks/dsr1_fp4_mi355x_docker.sh b/benchmarks/dsr1_fp4_mi355x_docker.sh
index ca1255802..8b3750a64 100644
--- a/benchmarks/dsr1_fp4_mi355x_docker.sh
+++ b/benchmarks/dsr1_fp4_mi355x_docker.sh
@@ -11,6 +11,7 @@
 # RESULT_FILENAME
 # NUM_PROMPTS
 export SGLANG_USE_AITER=1
+export ROCM_QUICK_REDUCE_QUANTIZATION=INT4
 
 PREFILL_SIZE=196608
 if [[ "$ISL" == "8192" && "$OSL" == "1024" ]]; then
@@ -30,7 +31,9 @@ python3 -m sglang.launch_server --model-path=$MODEL --trust-remote-code \
 --disable-radix-cache \
 --num-continuous-decode-steps=4 \
 --max-prefill-tokens=$PREFILL_SIZE \
---cuda-graph-max-bs=128 > $SERVER_LOG 2>&1 &
+--cuda-graph-max-bs=128 \
+--attention-backend aiter \
+--kv-cache-dtype fp8_e4m3 > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
 
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 112145f10..926ac7e1d 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -81,3 +81,8 @@
     - Update vLLM image for NVIDIA configs from vLLM 0.11.0 to vLLM 0.11.2
     - Adds kv-cache-dtype: fp8 to benchmarks/gptoss_fp4_b200_docker.sh
     PR: https://github.com/InferenceMAX/InferenceMAX/pull/273
+- config-keys:
+    - dsr1-fp4-mi355x-sglang
+  description: |
+    - Updating MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.6.post1 
+    PR: https://github.com/InferenceMAX/InferenceMAX/pull/330