diff --git a/tests/integration/defs/perf/pytorch_model_config.py b/tests/integration/defs/perf/pytorch_model_config.py
index 5d788731207a..0dbf1a91ee1d 100644
--- a/tests/integration/defs/perf/pytorch_model_config.py
+++ b/tests/integration/defs/perf/pytorch_model_config.py
@@ -251,6 +251,23 @@ def get_model_yaml_config(model_label: str,
                 'enable_attention_dp': True,
             }
         },
+        # MiniMax-M2.5 FP8 on 8 GPUs: intermediate_size=1536 with weight_block_size=128
+        # is not divisible under TP=8 (1536/8=192), so route MoE through EP=8 and use
+        # attention DP instead of TP.
+        {
+            'patterns': [
+                'minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:128,128-ep:8-gpus:8',
+                'minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:500,2000-ep:8-gpus:8',
+                'minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:2000,500-ep:8-gpus:8',
+                'minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:1000,1000-ep:8-gpus:8',
+                'minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:1000,2000-ep:8-gpus:8',
+                'minimax_m2.5_fp8-bench-pytorch-float8-maxbs:1-input_output_len:1000,1000-reqs:10-con:1-ep:8-gpus:8',
+                'minimax_m2.5_fp8-bench-pytorch-float8-maxbs:512-input_output_len:1000,1000-con:512-ep:8-gpus:8',
+            ],
+            'config': {
+                'enable_attention_dp': True,
+            }
+        },
         {
             'patterns': [
                 'qwen3_4b-bench-pytorch-streaming-bfloat16-maxbs:4-kv_frac:0.6-input_output_len:500,100-reqs:200-con:4',
diff --git a/tests/integration/test_lists/qa/llm_perf_core.yml b/tests/integration/test_lists/qa/llm_perf_core.yml
index 427cdd7b9e9a..b4752b6cbca1 100644
--- a/tests/integration/test_lists/qa/llm_perf_core.yml
+++ b/tests/integration/test_lists/qa/llm_perf_core.yml
@@ -317,6 +317,14 @@ llm_perf_core:
   #llama_v3.3_70b_instruct_fp8
   #pytorch backend
   - perf/test_perf.py::test_perf[llama_v3.3_70b_instruct_fp8-bench-pytorch-float8-maxbs:4096-maxnt:20000-kv_frac:0.85-input_output_len:20000,2000-reqs:1000-tp:8-gpus:8] TIMEOUT(120)
+  #minimax_m2.5 (FP8 216G, 8-GPU) - use EP=8 + attention DP; TP=8 would split intermediate_size 1536/8=192 (not divisible by 128 block size)
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:128,128-ep:8-gpus:8]
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:500,2000-ep:8-gpus:8]
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:2000,500-ep:8-gpus:8]
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:1000,1000-ep:8-gpus:8]
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:1000,2000-ep:8-gpus:8]
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-maxbs:1-input_output_len:1000,1000-reqs:10-con:1-ep:8-gpus:8] #min_latency
+  - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-maxbs:512-input_output_len:1000,1000-con:512-ep:8-gpus:8] #max_throughput
 # 9: H20, H200, B200, B300 test cases
   - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:128,128-tp:8-gpus:8]
   - perf/test_perf.py::test_perf[minimax_m2.5_fp8-bench-pytorch-float8-input_output_len:500,2000-tp:8-gpus:8]