pub struct DenseFfnWeightsFp8 {
pub gate_proj: Fp8Weight,
pub up_proj: Fp8Weight,
pub down_proj: Fp8Weight,
}Expand description
Native block-scaled FP8 dense MLP weights — loaded directly from an FP8
checkpoint (no NVFP4 requant). When installed via set_fp8_weights, decode
dispatches w8a16_gemv and prefill w8a16_gemm per projection (BF16 act ×
FP8 E4M3 weight with 2D block scales), mirroring the SSM/attention FP8 path.
Fields§
§gate_proj: Fp8Weight§up_proj: Fp8Weight§down_proj: Fp8WeightAuto Trait Implementations§
impl Freeze for DenseFfnWeightsFp8
impl RefUnwindSafe for DenseFfnWeightsFp8
impl Send for DenseFfnWeightsFp8
impl Sync for DenseFfnWeightsFp8
impl Unpin for DenseFfnWeightsFp8
impl UnwindSafe for DenseFfnWeightsFp8
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more