Function nvfp4_proj_small_m_same_input 

pub fn nvfp4_proj_small_m_same_input(
    gpu: &dyn GpuBackend,
    batch_kernel: KernelHandle,
    input: DevicePtr,
    weight: &QuantizedWeight,
    output: DevicePtr,
    m: u32,
    n: u32,
    k: u32,
    stream: u64,
) -> Result<()>

2026-09-25: nvfp4_proj_small_m for a projection whose input is byte for byte the input of the preceding projection on this stream (attention k/v after q, FFN up after gate). It skips re-quantising when the previous W4A4 quantisation was of exactly (backend, input, m, k, stream), and otherwise quantises as usual, so a wrong claim about the address cannot read a stale quantisation. The caller guarantees the contents did not change in between.