baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Formatting

Browse source
This commit is contained in:
Andrei Betlen 2023-04-08 16:01:18 -04:00
parent 0a5c551371
commit 0067c1a588
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llama_cpp/server/__main__.py
View file

@ -30,7 +30,7 @@ class Settings(BaseSettings):
n_batch: int = 8
n_threads: int = ((os.cpu_count() or 2) // 2) or 1
f16_kv: bool = True
use_mlock: bool = False # This causes a silent failure on platforms that don't support mlock (e.g. Windows) took forever to figure out...
use_mlock: bool = False # This causes a silent failure on platforms that don't support mlock (e.g. Windows) took forever to figure out...
embedding: bool = True
last_n_tokens_size: int = 64