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

Bump llama-cpp-python to 0.2.11

Browse source
This commit is contained in:
jllllll 2023-10-01 18:08:10 -05:00
parent f2d82f731a
commit 41a2de96e5
No known key found for this signature in database
GPG key ID: 7FCD00C417935797
14 changed files with 25 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -117,7 +117,6 @@ parser.add_argument('--use_double_quant', action='store_true', help='use_double_
parser.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
parser.add_argument('--n_batch', type=int, default=512, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
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.')