[Rust Frontend] Add dynamic LoRA endpoints (#43778)
Signed-off-by: xunzhuo <xunzhuo@vllm-semantic-router.ai> Co-authored-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
@@ -87,6 +87,17 @@ fn serve_args_auto_forward_python_flags_without_separator() {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn serve_args_auto_forward_enable_lora_to_python() {
|
||||
let cli =
|
||||
Cli::try_parse_from(["vllm-rs", "serve", "Qwen/Qwen3-0.6B", "--enable-lora"]).unwrap();
|
||||
|
||||
let Command::Serve(args) = cli.command else {
|
||||
panic!("expected serve args");
|
||||
};
|
||||
assert_eq!(args.managed_engine.python_args, vec!["--enable-lora"]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn serve_args_auto_forward_python_multi_char_alias_without_separator() {
|
||||
let cli = Cli::try_parse_from(["vllm-rs", "serve", "Qwen/Qwen3-0.6B", "-tp", "2"]).unwrap();
|
||||
|
||||
@@ -326,15 +326,6 @@ pub struct EngineUnsupportedArgs {
|
||||
#[arg(long)]
|
||||
pub mm_processor_cache_type: Option<Unsupported>,
|
||||
|
||||
/// If True, enable handling of LoRA adapters.
|
||||
#[arg(
|
||||
long,
|
||||
visible_alias = "no-enable-lora",
|
||||
default_missing_value = "true",
|
||||
num_args = 0..=1
|
||||
)]
|
||||
pub enable_lora: Option<Unsupported>,
|
||||
|
||||
/// Dictionary mapping specific modalities to LoRA model paths.
|
||||
#[arg(long)]
|
||||
pub default_mm_loras: Option<Unsupported>,
|
||||
|
||||
Reference in New Issue
Block a user