pub enum OpClass {
Ffn = 0,
Matvec = 1,
Matmat = 2,
Batch = 3,
MatmatWide = 4,
}Expand description
GPU-eligible op classes, each with an independent probe.
Variants§
Ffn = 0
Whole FFN chain in one submission (dense / MoE block).
Matvec = 1
Large hybrid CPU∥GPU matvec (lm_head class).
Matmat = 2
Prefill GEMM (matmat).
Batch = 3
Batched matvecs of one input (QKV).
MatmatWide = 4
Prefill GEMM at image-diffusion widths (b ≥ 128). Probed apart
from Matmat: one imagegen process runs BOTH populations
(prompt encode b≈40 where the GPU wins big, DiT b≥256 where
the CPU AMX arm is competitive) — a single shared verdict locks
the wrong arm for whichever population samples second.
Trait Implementations§
Auto Trait Implementations§
impl Freeze for OpClass
impl RefUnwindSafe for OpClass
impl Send for OpClass
impl Sync for OpClass
impl Unpin for OpClass
impl UnsafeUnpin for OpClass
impl UnwindSafe for OpClass
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