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 12, 14:45 UTC
[Tests] Verify gpt_oss package is installed in harmony tests (#29336)
Signed-off-by: Nick Hill <nhill@redhat.com>
Nick Hill committed
Nov 24, 2025 at 14:04 UTC
84371daf75507c849a38a9a44b2fb2af89e96dd3
1 file changed
+5
-1
tests/entrypoints/openai/test_response_api_with_harmony.py
+5
-1
@@ -1,6 +1,6 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
-
3
+import importlib
4
import json
5
import time
6
@@ -35,6 +35,10 @@ GET_WEATHER_SCHEMA = {
35
36
@pytest.fixture(scope="module")
37
def server():
38
+ assert importlib.util.find_spec("gpt_oss") is not None, (
39
+ "Harmony tests require gpt_oss package to be installed"
40
+ )
41
+
42
args = ["--enforce-eager", "--tool-server", "demo", "--max_model_len", "5000"]
43
env_dict = dict(
44
VLLM_ENABLE_RESPONSES_API_STORE="1",