Struct GpuConfig 

pub struct GpuConfig {
    pub backend: GpuBackend,
    pub device_id: usize,
    pub memory_limit_mb: Option<usize>,
    pub batch_size: usize,
    pub n_streams: usize,
    pub mixed_precision: bool,
    pub tensor_cores: bool,
    pub memory_pool_size_mb: usize,
    pub enable_profiling: bool,
}

GPU configuration

Fields

backend: GpuBackend

GPU backend to use

device_id: usize

Device ID (for systems with multiple GPUs)

memory_limit_mb: Option<usize>

Memory limit for GPU usage (in MB)

batch_size: usize

Batch size for GPU operations

n_streams: usize

Number of GPU streams for parallel execution

mixed_precision: bool

Enable mixed precision (FP16/FP32)

tensor_cores: bool

Enable tensor cores (for supported hardware)

memory_pool_size_mb: usize

Memory pool size for efficient allocation

enable_profiling: bool

Enable profiling for performance analysis

Trait Implementations

impl Clone for GpuConfig

fn clone(&self) -> GpuConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GpuConfig

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

Formats the value using the given formatter.

impl Default for GpuConfig

fn default() -> Self

Returns the “default value” for a type.