H200 MINIMAX vLLM extend configs

.github/configs/nvidia-master.yaml

@@ -3428,15 +3428,15 @@ minimaxm2.5-fp8-h200-vllm:
   - isl: 1024
     osl: 1024
     search-space:
-    - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, conc-start: 4, conc-end: 128 }
   - isl: 1024
     osl: 8192
     search-space:
-    - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, conc-start: 4, conc-end: 128 }
   - isl: 8192
     osl: 1024
     search-space:
-    - { tp: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 8, conc-start: 4, conc-end: 128 }
 
 dsr1-fp4-gb200-dynamo-trt:
   image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.8.1.post2

benchmarks/single_node/minimaxm2.5_fp8_h200.sh

@@ -5,6 +5,7 @@ source "$(dirname "$0")/../benchmark_lib.sh"
 check_env_vars \
     MODEL \
     TP \
+    EP_SIZE \
     CONC \
     ISL \
     OSL \
@@ -21,9 +22,16 @@ hf download "$MODEL"
 SERVER_LOG=/workspace/server.log
 PORT=${PORT:-8888}
 
+if [ "$EP_SIZE" -ge 1 ]; then
+  EP=" --enable-expert-parallel"
+else
+  EP=" "
+fi
+
 set -x
 vllm serve $MODEL --port $PORT \
 --tensor-parallel-size=$TP \
+$EP \
 --gpu-memory-utilization 0.95 \
 --max-model-len $MAX_MODEL_LEN \
 --disable-log-requests \

perf-changelog.yaml

@@ -931,4 +931,9 @@
     - "Switch to --attention-backend ROCM_AITER_UNIFIED_ATTN and add fuse_rope_kvcache compilation pass"
     - "Remove deprecated VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION/VLLM_ROCM_USE_AITER_MHA env vars and compilation-config cudagraph_mode"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/867
-
+
+- config-keys:
+    - minimaxm2.5-fp8-h200-vllm
+  description:
+    - "Extend MiniMax M2.5 FP8 single-node config for H200 with vLLM v0.16.0 (TP8)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/869