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

Add --mul_mat_q param

Browse source
This commit is contained in:
oobabooga 2023-08-18 07:58:20 -07:00
parent 28cf5862af
commit 4ec42679e3
6 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -119,6 +119,7 @@ parser.add_argument('--n_batch', type=int, default=512, help='Maximum number of
parser.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
parser.add_argument('--low-vram', action='store_true', help='Low VRAM Mode')
parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
parser.add_argument('--mul_mat_q', action='store_true', help='Activate new mulmat kernels.')
parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
parser.add_argument('--tensor_split', type=str, default=None, help="Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17")