Function gated_rms_norm_strided 

pub fn gated_rms_norm_strided(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    input: DevicePtr,
    gate: DevicePtr,
    weight: &DenseWeight,
    output: DevicePtr,
    heads_per_seq: u32,
    num_seqs: u32,
    hidden_size: u32,
    gate_stride: u32,
    eps: f32,
    group_size: u32,
    input_seq_stride: u32,
    gate_seq_stride: u32,
    output_seq_stride: u32,
    stream: u64,
) -> Result<()>

2026-09-25: Gated RMS norm of every (head, sequence) row of a multi-sequence decode in one launch: heads_per_seq rows per sequence, num_seqs sequences. Sequence strides count elements of each buffer’s own type: input_seq_stride in f32, gate_seq_stride and output_seq_stride in BF16.

The kernel, gated_rms_norm_f32_input_strided in kernels/gb10/common/rms_norm.cu, has the per-row body of gated_rms_norm_f32_input; only the row’s base address differs.