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

Add --no_use_cuda_fp16 param for AutoGPTQ

Browse source
This commit is contained in:
oobabooga 2023-06-23 12:22:56 -03:00
parent 5646690769
commit 3ae9af01aa
5 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -147,6 +147,7 @@ parser.add_argument('--autogptq', action='store_true', help='DEPRECATED')
parser.add_argument('--triton', action='store_true', help='Use triton.')
parser.add_argument('--no_inject_fused_attention', action='store_true', help='Do not use fused attention (lowers VRAM requirements).')
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('--no_use_cuda_fp16', action='store_true', help='This can make models faster on some systems.')
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