oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 07:03:37 +00:00
Code Issues Projects Releases Packages Wiki Activity

Fix several typos

Browse source
This commit is contained in:
oobabooga 2026-03-17 11:11:12 -07:00
parent 249861b65d
commit 2d141b54c5
5 changed files with 19 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -101,7 +101,7 @@ group.add_argument('--tensor-split', type=str, default=None, help='Split the mod
group.add_argument('--row-split', action='store_true', help='Split the model by rows across GPUs. This may improve multi-gpu performance.')
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('--no-kv-offload', action='store_true', help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')
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 performance.')
group.add_argument('--batch-size', type=int, default=1024, help='Maximum number of prompt tokens to batch together when calling llama-server. This is the application level batch size.')
group.add_argument('--ubatch-size', type=int, default=1024, help='Maximum number of prompt tokens to batch together when calling llama-server. This is the max physical batch size for computation (device level).')
group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')