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 17, 05:30 UTC
Remove unused const TIMEOUT_TO_PREVENT_DEADLOCK (#2321)
Ronen Schaffer committed
Jan 4, 2024 at 01:49 UTC
74d8d77626763bf7c4a2dd227231c69bb4638e29
1 file changed
-1
vllm/entrypoints/api_server.py
-1
@@ -12,7 +12,6 @@ from vllm.sampling_params import SamplingParams
12
from vllm.utils import random_uuid
13
14
TIMEOUT_KEEP_ALIVE = 5 # seconds.
15
-TIMEOUT_TO_PREVENT_DEADLOCK = 1 # seconds.
15
app = FastAPI()
16
engine = None
17