pub fn apply_router_lora(
gpu: &dyn GpuBackend,
kernels: &LoraKernels,
pair: &LoraPair,
router_in: DevicePtr,
gate_logits: DevicePtr,
n: u32,
max_rows: u32,
lora_xa: DevicePtr,
lora_delta: DevicePtr,
stream: u64,
) -> Result<()>Expand description
2026-09-25: Fold the router (mlp.gate) delta onto gate_logits
([n, num_experts], in place) from router_in ([n, hidden]), in blocks
of at most max_rows rows.