pub type KernelDTypes = SmallVec<[DType; 8]>;Expand description
Inline capacity for the per-operand dtype list in the binding-table key. 8 covers every op currently in flight without spilling to heap: PagedAttn (q + 2 caches + block_table + context_lens + alibi + out) at 7 entries is the worst case in inference; mixed-precision matmul is ≤ 4. Bumping later is one constant change.
Aliased Type§
pub struct KernelDTypes { /* private fields */ }