From fca2f948c101c9d520f1a381a6b705d9e11c042e Mon Sep 17 00:00:00 2001
From: wjunLu <135617475+wjunLu@users.noreply.github.com>
Date: Thu, 25 Dec 2025 09:18:05 +0800
Subject: [PATCH] [E2E Refactor] Enable skipped e2e case (#5287)

### What this PR does / why we need it?

The test case `tests/e2e/multicard/test_data_parallel.py` was skipped
due to the errors encountered during migration from Ascend A2 to A3, the
details are as follows
```
(EngineCore_DP0 pid=17833) RuntimeError: npu_moe_distribute_dispatch_v2:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:161 NPU function error: call aclnnMoeDistributeDispatchV3 failed, error code is 561002
(EngineCore_DP0 pid=17833) [ERROR] 2025-12-23-07:36:19 (PID:17833, Device:0, RankID:-1) ERR00100 PTA call acl api failed.
(EngineCore_DP0 pid=17833) EZ9999: Inner Error!
(EngineCore_DP0 pid=17833) EZ9999[PID: 17833] 2025-12-23-07:36:19.237.396 (EZ9999):  HCCL_BUFFSIZE is too SMALL, maxBs = 512, h = 2048, epWorldSize = 2, localMoeExpertNum = 64, sharedExpertNum = 0, tokenNeedSizeDispatch = 4608, tokenNeedSizeCombine = 4096, k = 8, NEEDED_HCCL_BUFFSIZE(((maxBs * tokenNeedSizeDispatch * ep_worldsize * localMoeExpertNum) + (maxBs * tokenNeedSizeCombine * (k + sharedExpertNum))) * 2) = 609MB, HCCL_BUFFSIZE=200MB.[FUNC:MoeDistributeDispatchA3TilingFuncImpl][FILE:moe_distribute_dispatch_v2_tiling.cc][LINE:941]
(EngineCore_DP0 pid=17833)         TraceBack (most recent call last):
(EngineCore_DP0 pid=17833)        MoeDistributeDispatchV2 do tiling failed, ret is -1.
(EngineCore_DP0 pid=17833)        Check NnopbaseExecutorDoTiling(executor) failed
(EngineCore_DP0 pid=17833)        Check NnopbaseExecutorTilingAndUpdateBinInfo(executor) failed
(EngineCore_DP0 pid=17833)        Check NnopbaseExecutorMatchCache(executor) failed
(EngineCore_DP0 pid=17833)        Check NnopbaseRunForWorkspace(*executor, workspaceSize) failed
```

### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
After fixed, I ran `pytest -sv --durations=0
tests/e2e/multicard/test_data_parallel.py`, and the result looks good
```
========================================================================================= warnings summary =========================================================================================
<frozen importlib._bootstrap>:241
  <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute

<frozen importlib._bootstrap>:241
  <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======================================================================================== slowest durations =========================================================================================
112.69s call     tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-vllm-ascend/Qwen3-30B-A3B-W8A8]
88.11s call     tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-Qwen/Qwen3-30B-A3B]
70.06s call     tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-Qwen/Qwen3-0.6B]

(6 durations < 0.005s hidden.  Use -vv to show these durations.)
============================================================================ 3 passed, 2 warnings in 270.88s (0:04:30) ============================================================================
```
- vLLM version: release/v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9

Signed-off-by: wjunLu <wjunlu217@gmail.com>
---
 tests/e2e/multicard/test_data_parallel.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/tests/e2e/multicard/test_data_parallel.py b/tests/e2e/multicard/test_data_parallel.py
index 6edeeb37..6b4df381 100644
--- a/tests/e2e/multicard/test_data_parallel.py
+++ b/tests/e2e/multicard/test_data_parallel.py
@@ -28,16 +28,14 @@ from unittest.mock import patch
 import pytest
 
 MODELS = [
-    "Qwen/Qwen3-0.6B",
-    "Qwen/Qwen3-30B-A3B",
-    # FIXME(Potabk): Skip this case for now
-    # "vllm-ascend/Qwen3-30B-A3B-W8A8"
+    "Qwen/Qwen3-0.6B", "Qwen/Qwen3-30B-A3B", "vllm-ascend/Qwen3-30B-A3B-W8A8"
 ]
 
 
 @pytest.mark.parametrize("model", MODELS)
 @pytest.mark.parametrize("max_tokens", [32])
 @patch.dict(os.environ, {"ASCEND_RT_VISIBLE_DEVICES": "0,1"})
+@patch.dict(os.environ, {"HCCL_BUFFSIZE": "1024"})
 def test_qwen3_inference_dp2(model, max_tokens):
     moe_models = ["Qwen/Qwen3-30B-A3B", "vllm-ascend/Qwen3-30B-A3B-W8A8"]
     quantization_models = ["vllm-ascend/Qwen3-30B-A3B-W8A8"]