Struct AcceleratorInfo 

pub struct AcceleratorInfo {
    pub kind: AcceleratorKind,
    pub gpu_layers: u32,
}

Snapshot of the active hardware-acceleration configuration.

kind is the compile-time GGML backend this engine was built with; gpu_layers is the runtime configuration the adapter was constructed with. A backend that compiled with cuda but was configured with n_gpu_layers = 0 reports kind = Cuda, gpu_layers = 0 — i.e. CUDA-capable but currently CPU-bound. The distinction is useful: it tells consumers the daemon could accelerate if reconfigured, vs. it can never accelerate without a rebuild.

Fields

kind: AcceleratorKind

Compile-time GGML backend.

gpu_layers: u32

Layers offloaded to the accelerator at construction time. 0 means CPU-only at runtime regardless of kind.

Trait Implementations

impl Clone for AcceleratorInfo

fn clone(&self) -> AcceleratorInfo

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AcceleratorInfo

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for AcceleratorInfo

fn default() -> AcceleratorInfo

Returns the “default value” for a type.

impl PartialEq for AcceleratorInfo

fn eq(&self, other: &AcceleratorInfo) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for AcceleratorInfo

impl Eq for AcceleratorInfo

impl StructuralPartialEq for AcceleratorInfo