Struct CpuGgufLinear 

pub struct CpuGgufLinear {
    pub store: CpuQuantStore,
    pub in_features: usize,
    pub out_features: usize,
}

CPU GGUF Linear: holds a CpuQuantStore (currently Q4_K-dequantised weights) plus shape, dispatches via CpuBackend::gemm.

Fields

store: CpuQuantStore

in_features: usize

out_features: usize

Trait Implementations

impl Linear<CpuBackend> for CpuGgufLinear

fn in_features(&self) -> usize

fn out_features(&self) -> usize

fn forward( &self, ctx: &mut <CpuBackend as Backend>::Context, input: &<CpuBackend as Backend>::Buffer, out: &mut <CpuBackend as Backend>::Buffer, m: usize, )

Append GEMM work onto ctx. Caller flushes the context when results must be materialised.

fn metadata(&self) -> LinearMetadata