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 14, 01:45 UTC
[CI] Fix flaky `test_two_responses_with_same_prev_id` test (#27745)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Oct 29, 2025 at 16:10 UTC
0f95a1c3f2d7b1b5e2ab8193cfb679dd8f64de63
1 file changed
+1
-1
tests/v1/entrypoints/openai/responses/conftest.py
+1
-1
@@ -6,7 +6,7 @@ import pytest_asyncio
6
from tests.utils import RemoteOpenAIServer
7
8
# Use a small reasoning model to test the responses API.
9
-MODEL_NAME = "Qwen/Qwen3-0.6B"
9
+MODEL_NAME = "Qwen/Qwen3-1.7B"
10
11
12
@pytest.fixture(scope="module")