oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-12-06 07:12:10 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update modules/shared.py

Browse source 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
oobabooga 2025-11-28 22:48:05 -03:00 committed by GitHub
parent 78b315344a
commit 5327bc9397
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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

@ -74,7 +74,7 @@ group.add_argument('--row-split', action='store_true', help='Split the model by
group.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.') 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('--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 the 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('--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('--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.') group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.') group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')