[Refactor] Relocate entrypoint tests to match serving code structure (#37593)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

.buildkite/scripts/hardware_ci/run-amd-test.sh

@@ -337,12 +337,16 @@ apply_rocm_test_overrides() {
     --ignore=entrypoints/openai/completion/test_shutdown.py \
     --ignore=entrypoints/openai/test_completion.py \
     --ignore=entrypoints/openai/models/test_models.py \
-    --ignore=entrypoints/openai/test_lora_adapters.py \
     --ignore=entrypoints/openai/test_return_tokens_as_ids.py \
     --ignore=entrypoints/openai/chat_completion/test_root_path.py \
     --ignore=entrypoints/openai/completion/test_prompt_validation.py "}
   fi
 
+  if [[ $cmds == *" entrypoints/serve"* ]]; then
+    cmds="${cmds} \
+    --ignore=entrypoints/serve/lora/test_lora_adapters.py"
+  fi
+
   if [[ $cmds == *" entrypoints/llm "* ]]; then
     cmds=${cmds//" entrypoints/llm "/" entrypoints/llm \
     --ignore=entrypoints/llm/test_chat.py \

tests/entrypoints/serve/disagg/test_serving_tokens.py

@@ -8,12 +8,11 @@ import pytest
 import pytest_asyncio
 from transformers import AutoTokenizer
 
+from tests.utils import RemoteOpenAIServer
 from vllm.config import ModelConfig
 from vllm.config.utils import getattr_iter
 from vllm.v1.engine.detokenizer import check_stop_strings
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "Qwen/Qwen3-0.6B"
 GEN_ENDPOINT = "/inference/v1/generate"
 

tests/entrypoints/serve/lora/test_lora_adapters.py

@@ -10,7 +10,7 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen3-0.6B"

tests/entrypoints/serve/render/test_launch_render.py

@@ -6,7 +6,7 @@ import httpx
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteLaunchRenderServer
+from tests.utils import RemoteLaunchRenderServer
 
 MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"