q2_0_mmq_gemm_packed

Function q2_0_mmq_gemm_packed 

Source
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

Q2_0 MMQ GEMM against a PackedQ2Weight (asserts group == 128, the only group the MMQ block layout supports — callers fall back to transient-dequant for group 64). Convenience over q2_0_mmq_gemm.