pub struct MtpFp8Experts {
pub experts: Vec<Fp8ExpertWeight>,
pub shared_expert: Fp8ExpertWeight,
}Expand description
2026-09-25: Native FP8 block-scaled MTP MoE tables: experts[e] is routed
expert e (all num_experts are loaded), plus the shared expert. The FP8
bytes belong to the weight store; only the FP32 block scales are owned
allocations.
Fields§
§experts: Vec<Fp8ExpertWeight>Auto Trait Implementations§
impl Freeze for MtpFp8Experts
impl RefUnwindSafe for MtpFp8Experts
impl Send for MtpFp8Experts
impl Sync for MtpFp8Experts
impl Unpin for MtpFp8Experts
impl UnwindSafe for MtpFp8Experts
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