oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-05 14:45:28 +00:00
Code Issues Projects Releases Packages Wiki Activity

Update the --tensor_split description

Browse source
This commit is contained in:
oobabooga 2024-07-20 22:04:48 -07:00
parent 916d1d8283
commit e9d4bff7d0
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -127,7 +127,7 @@ group.add_argument('--n_batch', type=int, default=512, help='Maximum number of p
group.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
group.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
group.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
group.add_argument('--tensor_split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17.')
group.add_argument('--tensor_split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.')
group.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
group.add_argument('--logits_all', action='store_true', help='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')
group.add_argument('--no_offload_kqv', action='store_true', help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')