[Fix] Add extra warmup run count for MC2 on specific SoC version (#4843)

### What this PR does / why we need it?
We didn’t account for this earlier because we didn’t have A3 in CI, but
now that we do, this test case needs a few extra tweaks — please take a
look at `profile_run`.

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

tests/e2e/multicard/test_aclgraph_capture_replay.py

@@ -25,6 +25,8 @@ import pytest
 import torch
 from vllm.utils.network_utils import get_open_port
 
+from vllm_ascend.utils import AscendDeviceType, get_ascend_device_type
+
 MODELS = [
     "Qwen/Qwen3-0.6B",
     "vllm-ascend/DeepSeek-V2-Lite-W8A8",
@@ -212,6 +214,10 @@ def test_aclgraph_capture_replay_dp2(
 
     # Part A: Warmup runs (Profile run + 2 runs per captured graph)
     warmup_runs = 1 + (2 * max_batch_sizes)
+    soc_version = get_ascend_device_type()
+    if soc_version in {AscendDeviceType._910_93} and "DeepSeek" in model:
+        # An extra warmup run is needed for MC2 warmup here
+        warmup_runs += 1
 
     # Part B: Alignment padding (Empty runs to hit the 32-step boundary)
     padding_runs = aligned_steps - total_steps