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, 19:30 UTC
[ci][distributed] shorten wait time if server hangs (#7098)
youkaichao committed
Aug 2, 2024 at 21:05 UTC
69ea15e5cc823b2bc040921ce516807fb7357dd1
1 file changed
+1
-1
tests/utils.py
+1
-1
@@ -50,7 +50,7 @@ VLLM_PATH = Path(__file__).parent.parent
50
51
class RemoteOpenAIServer:
52
DUMMY_API_KEY = "token-abc123" # vLLM's OpenAI server does not need API key
53
- MAX_SERVER_START_WAIT_S = 600 # wait for server to start for 60 seconds
53
+ MAX_SERVER_START_WAIT_S = 120 # wait for server to start for 120 seconds
54
55
def __init__(
56
self,