From e2d1c8b5e897e3f367af8bf026d6547f4b602be4 Mon Sep 17 00:00:00 2001
From: Flora Feng <4florafeng@gmail.com>
Date: Fri, 20 Mar 2026 01:31:23 -0400
Subject: [PATCH] [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              | 6 +++++-
 tests/entrypoints/openai/{ => responses}/test_protocol.py   | 0
 .../{ => openai/responses}/test_responses_utils.py          | 0
 tests/entrypoints/serve/disagg/__init__.py                  | 0
 .../{openai => serve/disagg}/test_serving_tokens.py         | 3 +--
 tests/entrypoints/serve/lora/__init__.py                    | 0
 .../{openai => serve/lora}/test_lora_adapters.py            | 2 +-
 .../{openai => serve/lora}/test_serving_models.py           | 0
 tests/entrypoints/serve/render/__init__.py                  | 0
 .../{openai => serve/render}/test_launch_render.py          | 2 +-
 .../test_embedding_shape_validation.py                      | 0
 11 files changed, 8 insertions(+), 5 deletions(-)
 rename tests/entrypoints/openai/{ => responses}/test_protocol.py (100%)
 rename tests/entrypoints/{ => openai/responses}/test_responses_utils.py (100%)
 create mode 100644 tests/entrypoints/serve/disagg/__init__.py
 rename tests/entrypoints/{openai => serve/disagg}/test_serving_tokens.py (99%)
 create mode 100644 tests/entrypoints/serve/lora/__init__.py
 rename tests/entrypoints/{openai => serve/lora}/test_lora_adapters.py (99%)
 rename tests/entrypoints/{openai => serve/lora}/test_serving_models.py (100%)
 create mode 100644 tests/entrypoints/serve/render/__init__.py
 rename tests/entrypoints/{openai => serve/render}/test_launch_render.py (99%)
 rename tests/{entrypoints/openai => multimodal}/test_embedding_shape_validation.py (100%)

diff --git a/.buildkite/scripts/hardware_ci/run-amd-test.sh b/.buildkite/scripts/hardware_ci/run-amd-test.sh
index f6b9f514ce4..4cacc2710f1 100755
--- a/.buildkite/scripts/hardware_ci/run-amd-test.sh
+++ b/.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 \
diff --git a/tests/entrypoints/openai/test_protocol.py b/tests/entrypoints/openai/responses/test_protocol.py
similarity index 100%
rename from tests/entrypoints/openai/test_protocol.py
rename to tests/entrypoints/openai/responses/test_protocol.py
diff --git a/tests/entrypoints/test_responses_utils.py b/tests/entrypoints/openai/responses/test_responses_utils.py
similarity index 100%
rename from tests/entrypoints/test_responses_utils.py
rename to tests/entrypoints/openai/responses/test_responses_utils.py
diff --git a/tests/entrypoints/serve/disagg/__init__.py b/tests/entrypoints/serve/disagg/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/tests/entrypoints/openai/test_serving_tokens.py b/tests/entrypoints/serve/disagg/test_serving_tokens.py
similarity index 99%
rename from tests/entrypoints/openai/test_serving_tokens.py
rename to tests/entrypoints/serve/disagg/test_serving_tokens.py
index 6cd4fd7a1e1..b62cb01bb45 100644
--- a/tests/entrypoints/openai/test_serving_tokens.py
+++ b/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"
 
diff --git a/tests/entrypoints/serve/lora/__init__.py b/tests/entrypoints/serve/lora/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/tests/entrypoints/openai/test_lora_adapters.py b/tests/entrypoints/serve/lora/test_lora_adapters.py
similarity index 99%
rename from tests/entrypoints/openai/test_lora_adapters.py
rename to tests/entrypoints/serve/lora/test_lora_adapters.py
index d5aa730ddce..a22f0b38991 100644
--- a/tests/entrypoints/openai/test_lora_adapters.py
+++ b/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"
diff --git a/tests/entrypoints/openai/test_serving_models.py b/tests/entrypoints/serve/lora/test_serving_models.py
similarity index 100%
rename from tests/entrypoints/openai/test_serving_models.py
rename to tests/entrypoints/serve/lora/test_serving_models.py
diff --git a/tests/entrypoints/serve/render/__init__.py b/tests/entrypoints/serve/render/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/tests/entrypoints/openai/test_launch_render.py b/tests/entrypoints/serve/render/test_launch_render.py
similarity index 99%
rename from tests/entrypoints/openai/test_launch_render.py
rename to tests/entrypoints/serve/render/test_launch_render.py
index 12e95e21991..37859e01f80 100644
--- a/tests/entrypoints/openai/test_launch_render.py
+++ b/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"
 
diff --git a/tests/entrypoints/openai/test_embedding_shape_validation.py b/tests/multimodal/test_embedding_shape_validation.py
similarity index 100%
rename from tests/entrypoints/openai/test_embedding_shape_validation.py
rename to tests/multimodal/test_embedding_shape_validation.py