mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

gpu-memory arg change

Browse source
This commit is contained in:
luis 2023-02-23 18:43:55 -05:00
parent 9ae063e42b
commit 5abdc99a7c
2 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -44,7 +44,7 @@ parser.add_argument('--bf16', action='store_true', help='Load the model with bfl
parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.')
parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.')
parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".')
parser.add_argument('--gpu-memory', type=int, help='Maximum GPU memory in GiB to allocate. This is useful if you get out of memory errors while trying to generate text. Must be an integer number.')
parser.add_argument('--gpu-memory', type=str, help='Maxmimum GPU memory in GiB to be allocated per GPU. Ex to allocate 11 GiB on device 0 and 5 GiB on device 1, use --gpu-memory 11,5')
parser.add_argument('--cpu-memory', type=int, help='Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.')
parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.')
parser.add_argument('--percent', nargs="+", type=int, default=[0, 100, 100, 0, 100, 0], help='FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0).')