[Core] Pipeline Parallel Support (#4412)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

tests/entrypoints/openai/test_completion.py

@@ -16,7 +16,7 @@ from openai import BadRequestError
 
 from vllm.transformers_utils.tokenizer import get_tokenizer
 
-from ...utils import RemoteOpenAIServer
+from ...utils import VLLM_PATH, RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
@@ -79,7 +79,7 @@ def zephyr_lora_files():
 
 @pytest.fixture(scope="module")
 def ray_ctx():
-    ray.init()
+    ray.init(runtime_env={"working_dir": VLLM_PATH})
     yield
     ray.shutdown()