oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-01-07 09:10:16 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Prevent llamacpp defaults from locking up consumer hardware (#6870)

Browse source
This commit is contained in:
Matthew Jenkins 2025-04-24 22:38:57 -04:00 committed by GitHub
parent 370fe7b7cf
commit 8f2493cc60
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

@ -120,7 +120,7 @@ group.add_argument('--flash-attn', action='store_true', help='Use flash-attentio
group.add_argument('--n_ctx', type=int, default=8192, help='Size of the prompt context.')
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('--batch-size', type=int, default=2048, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
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('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')