Add W8A8_DYNAMIC quantization inference test

The model of chosen is vllm-ascend/DeepSeek-V2-Lite-W8A8.

Signed-off-by: sdmyzlp <lrwei2@petalmail.com>

Author: sdmyzlp

.github/workflows/vllm_ascend_test.yaml

@@ -188,6 +188,7 @@ jobs:
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_topk
+            VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W8A8
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/ --ignore=tests/multicard/test_ilama_lora_tp2.py --ignore=tests/multicard/test_offline_inference_distributed.py
           fi
 
@@ -218,5 +219,6 @@ jobs:
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_topk
+            VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W8A8
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/ --ignore=tests/multicard/test_ilama_lora_tp2.py --ignore=tests/multicard/test_offline_inference_distributed.py
           fi

tests/multicard/test_offline_inference_distributed.py

@@ -23,7 +23,7 @@
 import os
 from unittest.mock import patch
 
-import vllm  # noqa: F401
+from modelscope import snapshot_download  # type: ignore
 from vllm import SamplingParams
 
 from tests.conftest import VllmRunner
@@ -95,3 +95,20 @@ def test_models_distributed_DeepSeek_dbo():
             distributed_executor_backend="mp",
     ) as vllm_model:
         vllm_model.generate(example_prompts, sampling_params)
+
+
+def test_models_distributed_DeepSeek_W8A8():
+    example_prompts = [
+        "Hello, my name is",
+    ]
+    max_tokens = 5
+
+    with VllmRunner(
+            snapshot_download("vllm-ascend/DeepSeek-V2-Lite-W8A8"),
+            max_model_len=8192,
+            enforce_eager=True,
+            dtype="auto",
+            tensor_parallel_size=4,
+            quantization="ascend",
+    ) as vllm_model:
+        vllm_model.generate_greedy(example_prompts, max_tokens)