[Bugfix][CI/Build][Hardware][AMD] Install matching torchvision to fix AMD tests (#5949)

tests/entrypoints/test_openai_chat.py

@@ -14,7 +14,7 @@ import torch
 from huggingface_hub import snapshot_download
 from openai import BadRequestError
 
-from ..utils import VLLM_PATH, RemoteOpenAIServer
+from ..utils import 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(runtime_env={"working_dir": VLLM_PATH})
+    ray.init()
     yield
     ray.shutdown()