pub fn q2_0_mmq_gemm_packed(
gpu: &dyn GpuBackend,
kernel_nc: KernelHandle,
kernel_wc: KernelHandle,
a_q8: DevicePtr,
w: &PackedQ2Weight,
out_bf16: DevicePtr,
m: u32,
stream: u64,
) -> Result<()>Expand description
2026-09-25: q2_0_mmq_gemm on a PackedQ2Weight. Returns an error unless
w.group == 128, the group size of block_q2_0.