oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 15:13:38 +00:00
Code Issues Projects Releases Packages Wiki Activity

Add --autosplit flag for ExLlamaV2 (#5524)

Browse source
This commit is contained in:
oobabooga 2024-02-16 15:26:10 -03:00 • committed by GitHub
parent 4039999be5
commit a6730f88f7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 29 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -134,6 +134,7 @@ group.add_argument('--row_split', action='store_true', help='Split the model by
# ExLlamaV2
group = parser.add_argument_group('ExLlamaV2')
group.add_argument('--gpu-split', type=str, help='Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7.')
group.add_argument('--autosplit', action='store_true', help='Autosplit the model tensors across the available GPUs. This causes --gpu-split to be ignored.')
group.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequence length.')
group.add_argument('--cfg-cache', action='store_true', help='ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
group.add_argument('--no_flash_attn', action='store_true', help='Force flash-attention to not be used.')