xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-05 02:04:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update Help Text for --gpu-memory-utilization Argument (#2183)

Browse Source
This commit is contained in:
Suhong Moon 2023-12-18 14:33:24 -05:00 committed by GitHub
parent 1b7c791d60
commit 290e015c6c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/engine/arg_utils.py
View File

@ -156,11 +156,13 @@ class EngineArgs:
type=int,
default=EngineArgs.swap_space,
help='CPU swap space size (GiB) per GPU')
parser.add_argument('--gpu-memory-utilization',
type=float,
default=EngineArgs.gpu_memory_utilization,
help='the percentage of GPU memory to be used for '
'the model executor')
parser.add_argument(
'--gpu-memory-utilization',
type=float,
default=EngineArgs.gpu_memory_utilization,
help='the fraction of GPU memory to be used for '
'the model executor, which can range from 0 to 1.'
'If unspecified, will use the default value of 0.9.')
parser.add_argument('--max-num-batched-tokens',
type=int,
default=EngineArgs.max_num_batched_tokens,