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

Add gpu_split param to ExLlama

Browse source 
Adapted from code created by Ph0rk0z. Thank you Ph0rk0z.
This commit is contained in:
oobabooga 2023-06-16 20:49:36 -03:00
parent cb9be5db1c
commit 5f392122fd
6 changed files with 20 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
modules/shared.py
View file

@ -148,6 +148,9 @@ parser.add_argument('--no_inject_fused_attention', action='store_true', help='Do
parser.add_argument('--no_inject_fused_mlp', action='store_true', help='Triton mode only: Do not use fused MLP (lowers VRAM requirements).')
parser.add_argument('--desc_act', action='store_true', help='For models that don\'t have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
# ExLlama
parser.add_argument('--gpu-split', type=str, help="Comma-separated list of VRAM (in GB) to use per GPU device for model layers, e.g. 20,7,7")
# FlexGen
parser.add_argument('--flexgen', action='store_true', help='DEPRECATED')
parser.add_argument('--percent', type=int, nargs="+", 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).')