pub enum GroupedRouting {
Batched,
PerRow,
PerToken,
}Expand description
2026-09-26: Which router arithmetic forward_fp8_grouped_decode_routed runs.
Variants§
Batched
2026-09-27: The batched gate GEMM (NVFP4 or BF16) and the batched softmax or sigmoid
top-k: the MTP drafter and the METRALE_FP8_MOE_GROUPED_DECODE arm.
PerRow
2026-09-27: The router of MoeLayer::forward, row by row.
PerToken
2026-09-27: The router of MoeLayer::forward_batched with BF16 logits.
Trait Implementations§
Source§impl Clone for GroupedRouting
impl Clone for GroupedRouting
Source§fn clone(&self) -> GroupedRouting
fn clone(&self) -> GroupedRouting
Returns a duplicate of the value. Read more
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for GroupedRouting
impl Debug for GroupedRouting
Source§impl PartialEq for GroupedRouting
impl PartialEq for GroupedRouting
impl Copy for GroupedRouting
impl Eq for GroupedRouting
impl StructuralPartialEq for GroupedRouting
Auto Trait Implementations§
impl Freeze for GroupedRouting
impl RefUnwindSafe for GroupedRouting
impl Send for GroupedRouting
impl Sync for GroupedRouting
impl Unpin for GroupedRouting
impl UnwindSafe for GroupedRouting
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
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
§fn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
Checks if this value is equivalent to the given key. Read more
§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
§fn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
Compare self to
key and return true if they are equal.