A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 10, 09:00 UTC
[CI/Build] Separate out flaky responses API tests (#32110)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jan 11, 2026 at 21:01 UTC
a37453211120bfd7b94042d84f519918d0a3698f
10 files changed
+42
-9
.buildkite/test-amd.yaml
+16
-2
@@ -162,8 +162,7 @@ steps:
162
- tests/entrypoints/test_chat_utils
163
commands:
164
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
165
- - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/test_vision_embeds.py
166
- - pytest -v -s entrypoints/openai/test_vision_embeds.py
165
+ - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
166
- pytest -v -s entrypoints/test_chat_utils.py
167
168
- label: Entrypoints Integration Test (API Server 2)
@@ -200,6 +199,21 @@ steps:
199
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
200
- pytest -v -s entrypoints/pooling
201
202
+- label: Entrypoints Integration Test (Responses API)
203
+ timeout_in_minutes: 50
204
+ mirror_hardwares: [amdexperimental]
205
+ agent_pool: mi325_1
206
+ # grade: Blocking
207
+ working_dir: "/vllm-workspace/tests"
208
+ fast_check: true
209
+ torch_nightly: true
210
+ source_file_dependencies:
211
+ - vllm/
212
+ - tests/entrypoints/openai/responses
213
+ commands:
214
+ - export VLLM_WORKER_MULTIPROC_METHOD=spawn
215
+ - pytest -v -s entrypoints/openai/responses
216
+
217
- label: Distributed Tests (4 GPUs) # 35min
218
timeout_in_minutes: 50
219
mirror_hardwares: [amdexperimental]
.buildkite/test-pipeline.yaml
+13
-1
@@ -144,7 +144,7 @@ steps:
144
- tests/entrypoints/test_chat_utils
145
commands:
146
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
147
- - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/
147
+ - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
148
- pytest -v -s entrypoints/test_chat_utils.py
149
150
- label: Entrypoints Integration Test (API Server 2)
@@ -177,6 +177,18 @@ steps:
177
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
178
- pytest -v -s entrypoints/pooling
179
180
+- label: Entrypoints Integration Test (Responses API)
181
+ timeout_in_minutes: 50
182
+ mirror_hardwares: [amdexperimental]
183
+ working_dir: "/vllm-workspace/tests"
184
+ fast_check: true
185
+ torch_nightly: true
186
+ source_file_dependencies:
187
+ - vllm/
188
+ - tests/entrypoints/openai/responses
189
+ commands:
190
+ - pytest -v -s entrypoints/openai/responses
191
+
192
- label: Distributed Tests (4 GPUs) # 35min
193
timeout_in_minutes: 50
194
mirror_hardwares: [amdexperimental]
.buildkite/test_areas/entrypoints.yaml
+9
-2
@@ -34,10 +34,9 @@ steps:
34
- tests/entrypoints/test_chat_utils
35
commands:
36
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
37
- - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/
37
+ - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
38
- pytest -v -s entrypoints/test_chat_utils.py
39
40
-
40
- label: Entrypoints Integration (API Server 2)
41
timeout_in_minutes: 130
42
working_dir: "/vllm-workspace/tests"
@@ -64,6 +63,14 @@ steps:
63
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
64
- pytest -v -s entrypoints/pooling
65
66
+- label: Entrypoints Integration (Responses API)
67
+ timeout_in_minutes: 50
68
+ working_dir: "/vllm-workspace/tests"
69
+ source_file_dependencies:
70
+ - vllm/
71
+ - tests/entrypoints/openai/responses
72
+ commands:
73
+ - pytest -v -s entrypoints/openai/responses
74
75
- label: Entrypoints V1
76
timeout_in_minutes: 50
tests/entrypoints/openai/responses/__init__.py
tests/entrypoints/openai/responses/test_errors.py
renamed
tests/entrypoints/openai/responses/test_function_call_parsing.py
renamed
tests/entrypoints/openai/responses/test_harmony.py
renamed
+1
-1
@@ -12,7 +12,7 @@ from openai_harmony import (
12
Message,
13
)
14
15
-from ...utils import RemoteOpenAIServer
15
+from ....utils import RemoteOpenAIServer
16
17
MODEL_NAME = "openai/gpt-oss-20b"
18
tests/entrypoints/openai/responses/test_mcp_tools.py
renamed
+1
-1
@@ -9,7 +9,7 @@ from openai_harmony import ToolDescription, ToolNamespaceConfig
9
10
from vllm.entrypoints.tool_server import MCPToolServer
11
12
-from ...utils import RemoteOpenAIServer
12
+from ....utils import RemoteOpenAIServer
13
14
MODEL_NAME = "openai/gpt-oss-20b"
15
tests/entrypoints/openai/responses/test_parsable_context.py
renamed
+1
-1
@@ -8,7 +8,7 @@ import pytest
8
import pytest_asyncio
9
from openai import OpenAI
10
11
-from ...utils import RemoteOpenAIServer
11
+from ....utils import RemoteOpenAIServer
12
13
MODEL_NAME = "Qwen/Qwen3-8B"
14
tests/entrypoints/openai/responses/test_simple.py
renamed
+1
-1
@@ -6,7 +6,7 @@ import pytest
6
import pytest_asyncio
7
from openai import OpenAI
8
9
-from ...utils import RemoteOpenAIServer
9
+from ....utils import RemoteOpenAIServer
10
11
MODEL_NAME = "Qwen/Qwen3-8B"
12