reopen deepseek test on v1

Signed-off-by: MengqingCao <[email protected]>

Author: MengqingCao

tests/multicard/test_offline_inference_distributed.py

@@ -22,7 +22,6 @@
 """
 import os
 
-import pytest
 import vllm  # noqa: F401
 
 from tests.conftest import VllmRunner
@@ -47,7 +46,6 @@ def test_models_distributed_QwQ():
         vllm_model.generate_greedy(example_prompts, max_tokens)
 
 
-@pytest.mark.skipif(True, reason="wait for mla issue fixed on v1")
 def test_models_distributed_DeepSeek():
     example_prompts = [
         "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",