oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 22:27:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Minor doc changes

Browse source
This commit is contained in:
oobabooga 2024-02-06 06:35:01 -08:00
parent 8ee3cea7cb
commit acfbe6b3b3
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/shared.py
View file

@ -131,8 +131,8 @@ group.add_argument('--no_offload_kqv', action='store_true', help='Do not offload
group.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
group.add_argument('--row_split', action='store_true', help='Split the model by rows across GPUs. This may improve multi-gpu performance.')
# ExLlama
group = parser.add_argument_group('ExLlama')
# 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('--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.')