huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix bool args

Browse Source 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2025-02-07 15:29:05 +00:00
parent 1401418243
commit b77d05d3af
No known key found for this signature in database
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
backends/llamacpp/src/main.rs
View File

@ -52,19 +52,19 @@ struct Args {
numa: LlamacppNuma,
/// Use memory mapping for the model.
#[clap(default_value = "true", long, env)]
#[clap(long, env)]
use_mmap: bool,
/// Use memory locking to prevent swapping.
#[clap(default_value = "false", long, env)]
#[clap(long, env)]
use_mlock: bool,
/// Enable offloading of KQV operations to the GPU.
#[clap(default_value = "true", long, env)]
#[clap(long, env)]
offload_kqv: bool,
/// Enable flash attention for faster inference. (EXPERIMENTAL)
#[clap(default_value = "true", long, env)]
#[clap(long, env)]
flash_attention: bool,
/// Data type used for K cache.
@ -132,7 +132,7 @@ struct Args {
tokenizer_config_path: Option<String>,
/// Disable grammar support.
#[clap(long, env, default_value_t = false)]
#[clap(long, env)]
disable_grammar_support: bool,
/// Maximum number of inputs per request.