Skip to main content

Module model

Module model 

Source
Expand description

Model execution traits (Layer, lowering, kernel-launch argument packing).

Structs§

KernelInstance
A concrete, dtype-resolved kernel produced by a #[kernel(dtypes = [...])] dispatcher (or a kernel_group!).
KernelInstanceBackward
The backward half of a KernelInstance, when a paired backward kernel is declared via #[kernel(..., backward = ...)].

Enums§

LoweringMode
Whether a graph is being lowered for inference or training (training lowerings additionally wire up backward kernels).

Traits§

ExecutableOp
An op that has been lowered to a compilable kernel representation.
Lowering
Lowers a Graph into a DAG of ExecutableOps, ready to compile/execute.
Model
A compiled, runnable model.
RuntimeContext
A runtime execution context (device/stream handles, etc), threaded through arg-packing.
RuntimeOp
Encapsulates the runtime-dispatch behaviour for a compiled op node: how many activation inputs it takes, what parameter buffers it needs, how to pack kernel arguments, and how to compute the launch grid.

Type Aliases§

NodeId
A node index within a compiled model’s DAG.
RawPtr
Raw device pointer alias used by runtime arg-packing.