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, 12:15 UTC
[Fix] Documentation spacing in compilation config help text (#17342)
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Hyogeun Oh (오효근) committed
Apr 29, 2025 at 16:16 UTC
193e78e35d6f66bed5cec7414d5da2d3de777381
1 file changed
+1
-1
vllm/engine/arg_utils.py
+1
-1
@@ -866,7 +866,7 @@ class EngineArgs:
866
'-O',
867
type=CompilationConfig.from_cli,
868
default=None,
869
- help='torch.compile configuration for the model.'
869
+ help='torch.compile configuration for the model. '
870
'When it is a number (0, 1, 2, 3), it will be '
871
'interpreted as the optimization level.\n'
872
'NOTE: level 0 is the default level without '