diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml
index b9560803e..be45dceef 100644
--- a/.github/configs/amd-master.yaml
+++ b/.github/configs/amd-master.yaml
@@ -417,7 +417,7 @@ minimaxm2.5-fp8-mi300x-vllm:
     - { tp: 4, conc-start: 4, conc-end: 64 }
 
 minimaxm2.5-fp8-mi325x-vllm:
-  image: vllm/vllm-openai-rocm:v0.16.0
+  image: vllm/vllm-openai-rocm:v0.18.0
   model: MiniMaxAI/MiniMax-M2.5
   model-prefix: minimaxm2.5
   runner: mi325x
@@ -429,17 +429,17 @@ minimaxm2.5-fp8-mi325x-vllm:
     osl: 1024
     search-space:
     - { tp: 2, conc-start: 4, conc-end: 64 }
-    - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, ep: 8, conc-start: 4, conc-end: 512 }
   - isl: 1024
     osl: 8192
     search-space:
     - { tp: 2, conc-start: 4, conc-end: 64 }
-    - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, ep: 8, conc-start: 4, conc-end: 256 }
   - isl: 8192
     osl: 1024
     search-space:
     - { tp: 2, conc-start: 4, conc-end: 64 }
-    - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, ep: 8, conc-start: 4, conc-end: 256 }
 
 gptoss-fp4-mi300x-vllm:
   image: vllm/vllm-openai-rocm:v0.17.0
diff --git a/benchmarks/single_node/minimaxm2.5_fp8_mi325x.sh b/benchmarks/single_node/minimaxm2.5_fp8_mi325x.sh
index 6c9a2ef6b..7938de9ee 100755
--- a/benchmarks/single_node/minimaxm2.5_fp8_mi325x.sh
+++ b/benchmarks/single_node/minimaxm2.5_fp8_mi325x.sh
@@ -5,6 +5,7 @@ source "$(dirname "$0")/../benchmark_lib.sh"
 check_env_vars \
     MODEL \
     TP \
+    EP_SIZE \
     CONC \
     ISL \
     OSL \
@@ -30,16 +31,22 @@ export VLLM_ROCM_USE_AITER=1
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
 
+if [ "$EP_SIZE" -gt 1 ]; then
+  EP=" --enable-expert-parallel"
+else
+  EP=" "
+fi
+
 # Start GPU monitoring (power, temperature, clocks every second)
 start_gpu_monitor
 
 set -x
 vllm serve $MODEL --port $PORT \
 --tensor-parallel-size=$TP \
+$EP \
 --gpu-memory-utilization 0.95 \
 --max-model-len $MAX_MODEL_LEN \
 --block-size=32 \
---disable-log-requests \
 --no-enable-prefix-caching \
 --trust-remote-code > $SERVER_LOG 2>&1 &
 
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6b0689cbf..3f0dac605 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1074,6 +1074,13 @@
     - "dsr1-fp8-b200-sglang-mtp: v0.5.8-cu130-amd64 → v0.5.9-cu130"
     - "dsr1-fp8-h200-sglang: v0.5.9-cu129-amd64 → v0.5.9-cu130"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/943
+  
+- config-keys:
+    - minimaxm2.5-fp8-mi325x-vllm
+  description:
+    - "Upgrade vLLM ROCm image from v0.16.0 to v0.18.0"
+    - "Replace TP4 with TP8/EP8, add conc range 4-256"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/953
 
 - config-keys:
     - kimik2.5-fp4-mi355x-vllm