[DOC] MiniMax-M2.5 model intro (#7296)

### What this PR does / why we need it?
1. Add nightly test on MiniMax-M2.5 with deployment method on A3
2. Add MiniMax-M2.5 deployment introduction to vllm-ascend docs

- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: limuyuan <limuyuan3@huawei.com>
Signed-off-by: SparrowMu <52023119+SparrowMu@users.noreply.github.com>
Co-authored-by: limuyuan <limuyuan3@huawei.com>

.github/workflows/misc/model_list.json

@@ -239,6 +239,7 @@
       "vllm-ascend/vllm-eagle-llama-68m-random",
       "wemaster/deepseek_mtp_main_random_bf16",
       "wemaster/deepseek_mtp_main_random_w8a8_part",
-      "xlangai/OpenCUA-7B"
+      "xlangai/OpenCUA-7B",
+      "MiniMax/MiniMax-M2.5"
     ]
   }

.github/workflows/schedule_nightly_test_a3.yaml

@@ -261,6 +261,9 @@ jobs:
           - name: kimi-k2-thinking
             os: linux-aarch64-a3-16
             config_file_path: Kimi-K2-Thinking.yaml
+          - name: minimax-m2-5
+            os: linux-aarch64-a3-16
+            config_file_path: MiniMax-M2.5-A3.yaml
           - name: mtpx-deepseek-r1-0528-w8a8
             os: linux-aarch64-a3-16
             config_file_path: MTPX-DeepSeek-R1-0528-W8A8.yaml