Skip to main content

Crate incin_backends

Crate incin_backends 

Source
Expand description

Incin’s execution backends: the built-in CPU backend plus feature-gated CUDA, WGPU, Metal, and external Candle implementations behind one dispatch surface, with the capability registries and codegen helpers backend authors share.

Re-exports§

pub use dispatch::DispatchBackend;
pub use detect::detect_device;
pub use detect::detect_device_in;
pub use simd::simd_lanes;
pub use telemetry::set_emitter;

Modules§

backend_kind
Device-to-backend selection for the unified IncinBackend facade.
capability
Authoritative native-backend capability registrations.
capability_docs
The generated support tables in docs/capabilities.md (UX-013). The support tables in docs/capabilities.md, rendered from the registrations in crate::capability.
codegen
Unified cross-backend kernel emitter module (PRF-007).
cpu
Incin Cpu
detect
Runtime detection of the best device this machine can actually run on. Runtime detection of the best device this machine can actually run on.
dispatch
Runtime backend selection used by IncinBackend<_, Dyn>.
dist
Collective transport contracts and optional implementations. Distributed collective transport contracts.
external
Third-party backend integrations, and the conformance suite an author of one runs against their own backend.
nn_target
Central target-aware parameter materialization and NN layer initialization on TensorTarget.
prelude
Single import surface for backend authors.
simd
Compile-time SIMD lane-width resolution for type-specialized kernels.
target
A device value as the user-facing allocation target.
telemetry
Optional telemetry integration for incin-backends.

Type Aliases§

EngineBackend
Backend parameterized by a target execution engine.
IncinBackend
Unified backend selected by device.
NativeBackend
Backend bound directly to one native device kind.