Struct PoolConfig 

pub struct PoolConfig {
    pub max_tensors_per_size: usize,
    pub max_total_memory: usize,
    pub enable_analytics: bool,
    pub pre_allocate_sizes: Vec<Vec<usize>>,
    pub enable_cache_awareness: bool,
    pub memory_alignment: usize,
    pub auto_gc_threshold: f64,
    pub enable_adaptive_sizing: bool,
    pub pressure_check_interval_ms: u64,
    pub min_cache_tracked_size: usize,
}

Configuration for memory pool behavior

Fields

max_tensors_per_size: usize

Maximum number of tensors to keep in each size pool

max_total_memory: usize

Maximum total memory usage in bytes

enable_analytics: bool

Whether to enable memory usage analytics

pre_allocate_sizes: Vec<Vec<usize>>

Pre-allocate common tensor sizes

enable_cache_awareness: bool

Enable cache-aware allocation strategies

memory_alignment: usize

Memory alignment for cache-friendly allocations (bytes)

auto_gc_threshold: f64

Automatic garbage collection threshold (fragmentation score 0.0-1.0)

enable_adaptive_sizing: bool

Enable adaptive pool sizing based on usage patterns

pressure_check_interval_ms: u64

Memory pressure monitoring interval (milliseconds)

min_cache_tracked_size: usize

Minimum allocation size to track for cache analysis

Trait Implementations

impl Clone for PoolConfig

fn clone(&self) -> PoolConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PoolConfig

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

Formats the value using the given formatter.

impl Default for PoolConfig

fn default() -> Self

Returns the “default value” for a type.