[CI] Refactor CI (#952)

1. remove some useless test func and file
2. fix format.sh problem
3. enable full test for singlecard and multicard
4. move long term test to long_term folder. For this kind of test, it
only runs by labeled and daily test. Include: spec decode、accuracy test

## After refactor:
There are 4 test modules
- `singlecard`: contains the test running on one NPU. It'll be run for
each PR and daily test.
- `multicard`: contains the test running on multi NPUs. It'll be run for
each PR and daily test.
- `long_term`: contains the test that cost much time(Now include `spec
decode` and `accuracy` test). It'll be run for the PR with
`long-term-test` labeled and daily test.
- `e2e`: contains the test for doc and pd feature. It'll be run for the
PR with `pd-test` labeled and daily test.

## Todo:
1. some test are skipped, they should be fixed and reenabled in the
future.
2. pyhccl test for multicard doesn't work at all. It should be enabled
as well.
3. ensure long-term-test pass by daily test.

### Know issue
Now, `ready` labels is required to start pd test or long term test. And
when `long-term-test` or `pd-test` is labeled after another one, the old
labeled test will be re-run again. So the labeled test should be ran in
the following step:

1. decide which test need run, then label it. `long-term-test` or
`pd-test` or both.
2. add `ready-for-test` label, then the test will be ran.

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

tests/multicard/test_offline_inference_distributed.py

@@ -28,15 +28,9 @@ import vllm  # noqa: F401
 from tests.conftest import VllmRunner
 
 os.environ["PYTORCH_NPU_ALLOC_CONF"] = "max_split_size_mb:256"
-os.environ["VLLM_USE_MODELSCOPE"] = "True"
 
 
-@pytest.mark.parametrize("model, distributed_executor_backend", [
-    ("Qwen/QwQ-32B", "mp"),
-    ("deepseek-ai/DeepSeek-V2-Lite", "mp"),
-])
-def test_models_distributed(model: str,
-                            distributed_executor_backend: str) -> None:
+def test_models_distributed_QwQ():
     example_prompts = [
         "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",
         "Briefly describe the major milestones in the development of artificial intelligence from 1950 to 2020.",
@@ -45,14 +39,28 @@ def test_models_distributed(model: str,
     dtype = "half"
     max_tokens = 5
     with VllmRunner(
-            model,
+            "Qwen/QwQ-32B",
             dtype=dtype,
             tensor_parallel_size=4,
-            distributed_executor_backend=distributed_executor_backend,
+            distributed_executor_backend="mp",
     ) as vllm_model:
         vllm_model.generate_greedy(example_prompts, max_tokens)
 
 
-if __name__ == "__main__":
-    import pytest
-    pytest.main([__file__])
+@pytest.mark.skipif(os.getenv("VLLM_USE_V1") == "1",
+                    reason="deepseek v2 lite is not supported on v1")
+def test_models_distributed_DeepSeek():
+    example_prompts = [
+        "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",
+        "Briefly describe the major milestones in the development of artificial intelligence from 1950 to 2020.",
+        "Compare and contrast artificial intelligence with human intelligence in terms of processing information.",
+    ]
+    dtype = "half"
+    max_tokens = 5
+    with VllmRunner(
+            "deepseek-ai/DeepSeek-V2-Lite",
+            dtype=dtype,
+            tensor_parallel_size=4,
+            distributed_executor_backend="mp",
+    ) as vllm_model:
+        vllm_model.generate_greedy(example_prompts, max_tokens)