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 15, 17:15 UTC
[Misc] Fix test_sleep to use query parameters (#14373)
Signed-off-by: Lize Cai <lize.cai@sap.com> Signed-off-by: youkaichao <youkaichao@gmail.com> Co-authored-by: youkaichao <youkaichao@gmail.com>
Lize Cai committed
Mar 28, 2025 at 19:00 UTC
a10314c6b35c7bad4320286409d8b5e6d11aa56e
1 file changed
+2
-1
tests/entrypoints/openai/test_sleep.py
+2
-1
@@ -25,8 +25,9 @@ def test_sleep_mode():
25
"VLLM_SERVER_DEV_MODE": "1",
26
"CUDA_VISIBLE_DEVICES": "0"
27
}) as remote_server:
28
+
29
response = requests.post(remote_server.url_for("/sleep"),
29
- data={"level": "1"})
30
+ params={"level": "1"})
31
assert response.status_code == 200
32
response = requests.get(remote_server.url_for("/is_sleeping"))
33
assert response.status_code == 200