simcop2387/text-generation-webui-mirror
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-06-07 14:17:09 -04:00
Code Issues Projects Releases Packages Wiki Activity

Default --gpu-layers to 256

Browse source
This commit is contained in:
oobabooga 2025-05-06 17:51:55 -07:00
parent 760b4dd115
commit b28fa86db6
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -119,7 +119,7 @@ group.add_argument('--threads-batch', type=int, default=0, help='Number of threa
group.add_argument('--batch-size', type=int, default=256, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
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('--gpu-layers', '--n-gpu-layers', type=int, default=0, metavar='N', help='Number of layers to offload to the GPU.')
group.add_argument('--gpu-layers', '--n-gpu-layers', type=int, default=256, metavar='N', 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: 60,40.')
group.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
group.add_argument('--no-kv-offload', action='store_true', help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')