10000 Add low_vram to server settings · GavinChen1314/llama-cpp-python@1e20be6 · GitHub
[go: up one dir, main page]

Skip to content

Commit 1e20be6

Browse files
committed
Add low_vram to server settings
1 parent 44b83ca commit 1e20be6

File tree

1 file changed

+4
-0
lines changed

1 file changed

+4
-0
lines changed

llama_cpp/server/app.py

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -48,6 +48,10 @@ class Settings(BaseSettings):
4848
description="Use mmap.",
4949
)
5050
embedding: bool = Field(default=True, description="Whether to use embeddings.")
51+
low_vram: bool = Field(
52+
default=False,
53+
description="Whether to use less VRAM. This will reduce performance.",
54+
)
5155
last_n_tokens_size: int = Field(
5256
default=64,
5357
ge=0,

0 commit comments

Comments
 (0)
0