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
[Minor] Fix typo (#2166)
Co-authored-by: John-Saxon <zhang.xiangxuan@oushu.com>
JohnSaxon committed
Dec 18, 2023 at 15:28 UTC
bbe4466fd98a27f918bd498c9e64a736202a133e
1 file changed
+1
-1
vllm/engine/arg_utils.py
+1
-1
@@ -159,7 +159,7 @@ class EngineArgs:
159
parser.add_argument('--gpu-memory-utilization',
160
type=float,
161
default=EngineArgs.gpu_memory_utilization,
162
- help='the percentage of GPU memory to be used for'
162
+ help='the percentage of GPU memory to be used for '
163
'the model executor')
164
parser.add_argument('--max-num-batched-tokens',
165
type=int,