huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enable flash attention by default

Browse Source 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2025-01-31 16:07:10 +00:00
parent 3f199134f0
commit ae5bb789c2
No known key found for this signature in database
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backends/llamacpp/src/main.rs
View File

@ -57,7 +57,7 @@ struct Args {
use_mlock: bool,
/// Enable flash attention for faster inference. (EXPERIMENTAL)
#[clap(default_value = "false", long, env)]
#[clap(default_value = "true", long, env)]
flash_attention: bool,
/// TODO