Failure

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>

Author: Yikun

.github/workflows/vllm_ascend_test.yaml

@@ -201,7 +201,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-arm64-npu-1]
-        vllm_version: [main, v0.9.1]
+        vllm_version: [v0.9.1]
     name: singlecard e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -257,23 +257,7 @@ jobs:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
         run: |
-          pytest -sv tests/e2e/singlecard/test_offline_inference.py
-          pytest -sv tests/e2e/singlecard/test_ilama_lora.py
-          pytest -sv tests/e2e/singlecard/test_guided_decoding.py
-          pytest -sv tests/e2e/singlecard/test_camem.py
-          pytest -sv tests/e2e/singlecard/test_embedding.py
-          pytest -sv tests/e2e/singlecard/ \
-          --ignore=tests/e2e/singlecard/test_offline_inference.py \
-          --ignore=tests/e2e/singlecard/test_ilama_lora.py \
-          --ignore=tests/e2e/singlecard/test_guided_decoding.py \
-          --ignore=tests/e2e/singlecard/test_camem.py \
-          --ignore=tests/e2e/singlecard/test_embedding.py \
-          --ignore=tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py \
-          --ignore=tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
-          # ------------------------------------ v1 spec decode test ------------------------------------ #
-          VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
-          # TODO: revert me when test_v1_spec_decode.py::test_ngram_correctness is fixed
-          VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
+          pytest -sv tests/e2e/singlecard/test_aclgraph.py
 
       - name: Run e2e test on V0 engine
         if: ${{ github.event_name == 'schedule' }}

tests/e2e/singlecard/test_aclgraph.py

@@ -29,7 +29,7 @@
 from tests.conftest import VllmRunner
 from tests.model_utils import check_outputs_equal
 
-MODELS = ["Qwen/Qwen2.5-0.5B-Instruct"]
+MODELS = ["Qwen/Qwen2.5-0.5B-Instruct", "vllm-ascend/Qwen3-30B-A3B-Puring"]
 
 
 @pytest.mark.skipif(os.getenv("VLLM_USE_V1") == "0",