[AMD] Add Minimax tp8 with ep and update vllm image for MI355x

.github/configs/amd-master.yaml

@@ -360,7 +360,7 @@ kimik2.5-fp4-mi355x-vllm:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
 minimaxm2.5-fp8-mi355x-vllm:
-  image: vllm/vllm-openai-rocm:v0.15.1
+  image: vllm/vllm-openai-rocm:v0.18.0
   model: MiniMaxAI/MiniMax-M2.5
   model-prefix: minimaxm2.5
   runner: mi355x
@@ -373,16 +373,19 @@ minimaxm2.5-fp8-mi355x-vllm:
     search-space:
     - { tp: 2, conc-start: 4, conc-end: 64 }
     - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, ep: 8, conc-start: 32, conc-end: 256 }
   - 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: 32, 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: 32, conc-end: 256 }
 
 minimaxm2.5-fp8-mi300x-vllm:
   image: vllm/vllm-openai-rocm:v0.16.0

benchmarks/single_node/minimaxm2.5_fp8_mi355x.sh

@@ -5,6 +5,7 @@ source "$(dirname "$0")/../benchmark_lib.sh"
 check_env_vars \
     MODEL \
     TP \
+    EP_SIZE \
     CONC \
     ISL \
     OSL \
@@ -28,16 +29,22 @@ export VLLM_ROCM_USE_AITER=1
 SERVER_LOG=/workspace/server.log
 PORT=${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 \
 --trust-remote-code > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!

perf-changelog.yaml

@@ -994,3 +994,11 @@
     - "EAGLE speculative decoding: num-steps 3, draft-tokens 4, topk 1"
     - "New script: benchmarks/single_node/qwen3.5_fp8_b200_mtp.sh"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/898
+
+- config-keys:
+    - minimaxm2.5-fp8-mi355x-vllm
+  description:
+    - "ADD minimax TP=8 with EP, in config of 1k1k, 1k8k, and 8k1k sequence lengths"
+    - "Config concurrency: 32-256"
+    - "update image to vllm/vllm-openai-rocm:v0.18.0"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/927