diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml
index 9ef2a56ae9..e972d62a56 100644
--- a/.buildkite/test-amd.yaml
+++ b/.buildkite/test-amd.yaml
@@ -223,7 +223,7 @@ steps:
   - vllm/platforms/rocm.py
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
 
 
 - label: Entrypoints Integration (LLM) # TBD
@@ -254,11 +254,11 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/entrypoints/rpc
-  - tests/entrypoints/instrumentator
+  - tests/entrypoints/serve/instrumentator
   - tests/tool_use
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/instrumentator
+  - pytest -v -s entrypoints/serve/instrumentator
   - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
   - pytest -v -s tool_use
 
@@ -1475,11 +1475,11 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/entrypoints/rpc
-  - tests/entrypoints/instrumentator
+  - tests/entrypoints/serve/instrumentator
   - tests/tool_use
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/instrumentator
+  - pytest -v -s entrypoints/serve/instrumentator
   - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
   - pytest -v -s tool_use
 
@@ -2981,11 +2981,11 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/entrypoints/rpc
-  - tests/entrypoints/instrumentator
+  - tests/entrypoints/serve/instrumentator
   - tests/tool_use
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/instrumentator
+  - pytest -v -s entrypoints/serve/instrumentator
   - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
   - pytest -v -s tool_use
 
diff --git a/.buildkite/test_areas/entrypoints.yaml b/.buildkite/test_areas/entrypoints.yaml
index ac6be8e141..1f8dd08fb4 100644
--- a/.buildkite/test_areas/entrypoints.yaml
+++ b/.buildkite/test_areas/entrypoints.yaml
@@ -10,7 +10,7 @@ steps:
   - tests/entrypoints/
   commands:
   - pytest -v -s entrypoints/openai/tool_parsers
-  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/serve/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
 
 - label: Entrypoints Integration (LLM)
   timeout_in_minutes: 40
@@ -48,11 +48,11 @@ steps:
   source_file_dependencies:
   - vllm/
   - tests/entrypoints/rpc
-  - tests/entrypoints/instrumentator
+  - tests/entrypoints/serve/instrumentator
   - tests/tool_use
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/instrumentator
+  - pytest -v -s entrypoints/serve/instrumentator
   - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
   - pytest -v -s tool_use
 
diff --git a/tests/entrypoints/openai/cpu/__init__.py b/tests/entrypoints/openai/cpu/__init__.py
deleted file mode 100644
index e69de29bb2..0000000000
diff --git a/tests/entrypoints/instrumentator/__init__.py b/tests/entrypoints/serve/instrumentator/__init__.py
similarity index 100%
rename from tests/entrypoints/instrumentator/__init__.py
rename to tests/entrypoints/serve/instrumentator/__init__.py
diff --git a/tests/entrypoints/instrumentator/test_basic.py b/tests/entrypoints/serve/instrumentator/test_basic.py
similarity index 99%
rename from tests/entrypoints/instrumentator/test_basic.py
rename to tests/entrypoints/serve/instrumentator/test_basic.py
index 5f48fb266e..1ab963dc18 100644
--- a/tests/entrypoints/instrumentator/test_basic.py
+++ b/tests/entrypoints/serve/instrumentator/test_basic.py
@@ -11,11 +11,10 @@ import pytest_asyncio
 import requests
 from fastapi import Request
 
+from tests.utils import RemoteOpenAIServer
 from vllm.v1.engine.exceptions import EngineDeadError
 from vllm.version import __version__ as VLLM_VERSION
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "Qwen/Qwen3-0.6B"
 
 
diff --git a/tests/entrypoints/instrumentator/test_metrics.py b/tests/entrypoints/serve/instrumentator/test_metrics.py
similarity index 100%
rename from tests/entrypoints/instrumentator/test_metrics.py
rename to tests/entrypoints/serve/instrumentator/test_metrics.py
diff --git a/tests/entrypoints/instrumentator/test_optional_middleware.py b/tests/entrypoints/serve/instrumentator/test_optional_middleware.py
similarity index 98%
rename from tests/entrypoints/instrumentator/test_optional_middleware.py
rename to tests/entrypoints/serve/instrumentator/test_optional_middleware.py
index c2c7fbdb01..fef10cdc0c 100644
--- a/tests/entrypoints/instrumentator/test_optional_middleware.py
+++ b/tests/entrypoints/serve/instrumentator/test_optional_middleware.py
@@ -10,7 +10,7 @@ from http import HTTPStatus
 import pytest
 import requests
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # Use a small embeddings model for faster startup and smaller memory footprint.
 # Since we are not testing any chat functionality,
diff --git a/tests/entrypoints/instrumentator/test_orca_metrics.py b/tests/entrypoints/serve/instrumentator/test_orca_metrics.py
similarity index 98%
rename from tests/entrypoints/instrumentator/test_orca_metrics.py
rename to tests/entrypoints/serve/instrumentator/test_orca_metrics.py
index 1ce043df0c..9239513677 100644
--- a/tests/entrypoints/instrumentator/test_orca_metrics.py
+++ b/tests/entrypoints/serve/instrumentator/test_orca_metrics.py
@@ -5,7 +5,7 @@ import openai
 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/instrumentator/test_sleep.py b/tests/entrypoints/serve/instrumentator/test_sleep.py
similarity index 100%
rename from tests/entrypoints/instrumentator/test_sleep.py
rename to tests/entrypoints/serve/instrumentator/test_sleep.py
diff --git a/tests/entrypoints/openai/cpu/test_render.py b/tests/entrypoints/serve/render/test_render.py
similarity index 100%
rename from tests/entrypoints/openai/cpu/test_render.py
rename to tests/entrypoints/serve/render/test_render.py
diff --git a/tests/entrypoints/openai/cpu/test_render_multimodal.py b/tests/entrypoints/serve/render/test_render_multimodal.py
similarity index 100%
rename from tests/entrypoints/openai/cpu/test_render_multimodal.py
rename to tests/entrypoints/serve/render/test_render_multimodal.py