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

Add tensor split support for llama.cpp (#3171)

Browse source
This commit is contained in:
Shouyi 2023-07-26 07:59:26 +10:00 • committed by GitHub
parent f653546484
commit 031fe7225e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 20 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -125,6 +125,7 @@ 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('--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")
parser.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='Seed for llama-cpp models. Default 0 (random)')
parser.add_argument('--n_gqa', type=int, default=0, help='grouped-query attention. Must be 8 for llama2 70b.')