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

Streamline GPTQ-for-LLaMa support

Browse source
This commit is contained in:
jllllll 2023-08-09 23:42:34 -05:00
parent a3295dd666
commit bee73cedbd
No known key found for this signature in database
GPG key ID: 7FCD00C417935797
5 changed files with 21 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

3
modules/shared.py
View file

@ -138,9 +138,6 @@ parser.add_argument('--groupsize', type=int, default=-1, help='Group size.')
parser.add_argument('--pre_layer', type=int, nargs="+", help='The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. For multi-gpu, write the numbers separated by spaces, eg --pre_layer 30 60.')
parser.add_argument('--checkpoint', type=str, help='The path to the quantized checkpoint file. If not specified, it will be automatically detected.')
parser.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.')
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.')
# AutoGPTQ
parser.add_argument('--triton', action='store_true', help='Use triton.')