oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 14:17:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama.cpp: Add --extra-flags parameter for passing additional flags to llama-server

Browse source
This commit is contained in:
oobabooga 2025-04-25 07:32:51 -07:00
parent b6fffbd216
commit 98f4c694b9
5 changed files with 18 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -128,6 +128,7 @@ group.add_argument('--tensor-split', type=str, default=None, help='Split the mod
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.')
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('--extra-flags', type=str, default=None, help='Extra flags to pass to llama-server. Format: "flag1=value1;flag2;flag3=value3". Example: "override-tensor=exps=CPU"')
# Speculative decoding
group = parser.add_argument_group('Speculative decoding')