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

Change GPTQ triton default settings

Browse source
This commit is contained in:
oobabooga 2023-04-22 12:27:30 -03:00
parent e03b873460
commit 7438f4f6ba
3 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

6
modules/shared.py
View file

@ -124,9 +124,9 @@ parser.add_argument('--model_type', type=str, help='Model type of pre-quantized
parser.add_argument('--groupsize', type=int, default=-1, help='Group size.')
parser.add_argument('--pre_layer', type=int, default=0, help='The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models.')
parser.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.')
parser.add_argument('--no-quant_attn', action='store_true', help='(triton) Disable quant attention. If you encounter incoherent results try disabling this.')
parser.add_argument('--no-warmup_autotune', action='store_true', help='(triton) Disable warmup autotune.')
parser.add_argument('--no-fused_mlp', action='store_true', help='(triton) Disable fused mlp. If you encounter "Unexpected mma -> mma layout conversion" try disabling this.')
parser.add_argument('--quant_attn', action='store_true', help='(triton) Enable quant attention.')
parser.add_argument('--warmup_autotune', action='store_true', help='(triton) Enable warmup autotune.')
parser.add_argument('--fused_mlp', action='store_true', help='(triton) Enable fused mlp.')
# FlexGen
parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.')