skip v1 tests on non-cuda

tests/engine/v1/test_async_llm.py

@@ -5,8 +5,13 @@
 
 from vllm import SamplingParams
 from vllm.engine.arg_utils import AsyncEngineArgs
+from vllm.platforms import current_platform
 from vllm.v1.engine.async_llm import AsyncLLM
 
+if not current_platform.is_cuda():
+    pytest.skip(reason="V1 currently only supported on CUDA.",
+                allow_module_level=True)
+
 ENGINE_ARGS = AsyncEngineArgs(model="meta-llama/Llama-3.2-1B",
                               disable_log_requests=False)
 

tests/engine/v1/test_engine_core.py

@@ -1,15 +1,21 @@
 import time
 import uuid
 
+import pytest
 from transformers import AutoTokenizer
 
 from vllm import SamplingParams
 from vllm.engine.arg_utils import EngineArgs
+from vllm.platforms import current_platform
 from vllm.usage.usage_lib import UsageContext
 from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.engine.async_llm import AsyncLLM
 from vllm.v1.engine.core import EngineCore
 
+if not current_platform.is_cuda():
+    pytest.skip(reason="V1 currently only supported on CUDA.",
+                allow_module_level=True)
+
 MODEL_NAME = "meta-llama/Llama-3.2-1B-Instruct"
 TOKENIZER = AutoTokenizer.from_pretrained(MODEL_NAME)
 PROMPT = "Hello my name is Robert and I love quanitzation kernels"

tests/engine/v1/test_engine_core_client.py

@@ -8,11 +8,16 @@
 
 from vllm import SamplingParams
 from vllm.engine.arg_utils import EngineArgs
+from vllm.platforms import current_platform
 from vllm.usage.usage_lib import UsageContext
 from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.engine.async_llm import AsyncLLM
 from vllm.v1.engine.core_client import EngineCoreClient
 
+if not current_platform.is_cuda():
+    pytest.skip(reason="V1 currently only supported on CUDA.",
+                allow_module_level=True)
+
 MODEL_NAME = "meta-llama/Llama-3.2-1B-Instruct"
 TOKENIZER = AutoTokenizer.from_pretrained(MODEL_NAME)
 PROMPT = "Hello my name is Robert and I love quanitzation kernels"