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 16, 18:15 UTC
[ci][test] allow longer wait time for api server (#7629)
youkaichao committed
Aug 17, 2024 at 11:26 UTC
832163b8754efe2c6d74fbecb6a87a4119410db4
1 file changed
+1
-1
tests/utils.py
+1
-1
@@ -56,7 +56,7 @@ VLLM_PATH = Path(__file__).parent.parent
56
57
class RemoteOpenAIServer:
58
DUMMY_API_KEY = "token-abc123" # vLLM's OpenAI server does not need API key
59
- MAX_START_WAIT_S = 120 # wait for server to start for 120 seconds
59
+ MAX_START_WAIT_S = 240 # wait for server to start for 240 seconds
60
61
def __init__(
62
self,