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, 05:30 UTC
[CI] Increase timeout for test_completion_with_image_embeds (#22670)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Aug 11, 2025 at 23:31 UTC
93d0652433f9385959d5296a4dc1c98ec58f0d58
1 file changed
+2
-1
tests/v1/entrypoints/openai/test_completion_with_image_embeds.py
+2
-1
@@ -38,7 +38,8 @@ def default_image_embeds_server_args() -> list[str]:
38
@pytest.fixture(scope="module")
39
def server_with_image_embeds(default_image_embeds_server_args):
40
with RemoteOpenAIServer(MODEL_NAME,
41
- default_image_embeds_server_args) as remote_server:
41
+ default_image_embeds_server_args,
42
+ max_wait_seconds=600) as remote_server:
43
yield remote_server
44
45