Struct LoraRoute 

pub struct LoraRoute {
    pub a_table: DevicePtr,
    pub b_table: DevicePtr,
    pub scale_table: DevicePtr,
    pub k_in: u32,
    pub n_out: u32,
    pub max_rank: u32,
}

Frozen per-(layer,module) routing tables the bgmv reads: the [max_loras] device pointer tables (a_table/b_table, NULL=base) + the shared [max_loras] f32 scale_table, plus the projection dims. Load-time-fixed device addresses (built at pool pack time), so they are stable kernel args across CUDA-graph capture/replay — adapter identity flows ONLY through the per-step seq_slot buffer. Installed by copy onto the layer next to the active-slot LoraPair (which the single-seq n==1 path still uses).

Fields

a_table: DevicePtr

b_table: DevicePtr

scale_table: DevicePtr

k_in: u32

n_out: u32

max_rank: u32

Trait Implementations

impl Clone for LoraRoute

fn clone(&self) -> LoraRoute

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for LoraRoute

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Copy for LoraRoute