xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 09:05:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Doc] update gpu-memory-utilization flag docs (#9507)

Browse Source 
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
This commit is contained in:
Joe Runde 2024-10-18 22:26:36 -05:00 committed by GitHub
parent 1325872ec8
commit 82c25151ec
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/arg_utils.py
View File

@ -428,7 +428,11 @@ class EngineArgs:
help='The fraction of GPU memory to be used for the model ' help='The fraction of GPU memory to be used for the model '
'executor, which can range from 0 to 1. For example, a value of ' 'executor, which can range from 0 to 1. For example, a value of '
'0.5 would imply 50%% GPU memory utilization. If unspecified, ' '0.5 would imply 50%% GPU memory utilization. If unspecified, '
'will use the default value of 0.9.') 'will use the default value of 0.9. This is a global gpu memory '
'utilization limit, for example if 50%% of the gpu memory is '
'already used before vLLM starts and --gpu-memory-utilization is '
'set to 0.9, then only 40%% of the gpu memory will be allocated '
'to the model executor.')
parser.add_argument( parser.add_argument(
'--num-gpu-blocks-override', '--num-gpu-blocks-override',
type=int, type=int,