diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index c396e6788..0f6788569 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -22,7 +22,7 @@ dsr1-fp4-mi355x-sglang:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
 dsr1-fp8-mi300x-sglang:
-  image: rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi30x-20250915
+  image: lmsysorg/sglang:v0.5.5.post3-rocm700-mi30x
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi300x
@@ -44,7 +44,7 @@ dsr1-fp8-mi300x-sglang:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
 dsr1-fp8-mi325x-sglang:
-  image: rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi30x-20250915
+  image: lmsysorg/sglang:v0.5.5.post3-rocm700-mi30x
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi325x
@@ -66,7 +66,7 @@ dsr1-fp8-mi325x-sglang:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
 dsr1-fp8-mi355x-sglang:
-  image: rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915
+  image: lmsysorg/sglang:v0.5.5.post3-rocm700-mi35x
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: mi355x
diff --git a/benchmarks/dsr1_fp8_mi355x_docker.sh b/benchmarks/dsr1_fp8_mi355x_docker.sh
index d3abe2964..a2c6fec1b 100644
--- a/benchmarks/dsr1_fp8_mi355x_docker.sh
+++ b/benchmarks/dsr1_fp8_mi355x_docker.sh
@@ -15,10 +15,13 @@
 # https://rocm.docs.amd.com/en/docs-7.0-docker/benchmark-docker/inference-sglang-deepseek-r1-fp8.html
 
 export SGLANG_USE_AITER=1
+export RCCL_MSCCL_ENABLE=0
+export ROCM_QUICK_REDUCE_QUANTIZATION=INT4
 
 SERVER_LOG=$(mktemp /tmp/server-XXXXXX.log)
 
 python3 -m sglang.launch_server \
+    --attention-backend aiter \
     --model-path $MODEL \
     --host=0.0.0.0 \
     --port $PORT \
@@ -28,6 +31,7 @@ python3 -m sglang.launch_server \
     --mem-fraction-static 0.8 --disable-radix-cache \
     --num-continuous-decode-steps 4 \
     --max-prefill-tokens 196608 \
+    --enable-torch-compile \
     --cuda-graph-max-bs 128 > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/benchmarks/dsr1_fp8_mi355x_slurm.sh b/benchmarks/dsr1_fp8_mi355x_slurm.sh
index c046ede17..c6f0fade7 100644
--- a/benchmarks/dsr1_fp8_mi355x_slurm.sh
+++ b/benchmarks/dsr1_fp8_mi355x_slurm.sh
@@ -13,11 +13,14 @@
 # PORT_OFFSET
 
 export SGLANG_USE_AITER=1
+export RCCL_MSCCL_ENABLE=0
+export ROCM_QUICK_REDUCE_QUANTIZATION=INT4
 
 SERVER_LOG=$(mktemp /tmp/server-XXXXXX.log)
 PORT=$(( 8888 + $PORT_OFFSET ))
 
 python3 -m sglang.launch_server \
+    --attention-backend aiter \
     --model-path $MODEL \
     --host=0.0.0.0 \
     --port $PORT \
@@ -27,7 +30,8 @@ python3 -m sglang.launch_server \
     --mem-fraction-static 0.8 --disable-radix-cache \
     --num-continuous-decode-steps 4 \
     --max-prefill-tokens 196608 \
-    --cuda-graph-max-bs 128 > $SERVER_LOG 2>&1 &
+    --cuda-graph-max-bs 128 \
+    --enable-torch-compile > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
 
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6c3052a3e..c7f68885c 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -133,3 +133,11 @@
     - "Update vLLM image from v0.11.2 to v0.13.0"
     - "Add VLLM_MXFP4_USE_MARLIN=1 to H100 and H200 benchmark scripts"
   pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/327
+
+- config-keys:
+    - dsr1-fp8-mi300x-sglang
+    - dsr1-fp8-mi325x-sglang
+    - dsr1-fp8-mi355x-sglang
+  description:
+    - Use upstream SGLang images on mi300, mi325 and mi355 for dsr1fp8
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/332