Enum FitVerdict 

pub enum FitVerdict {
    RunsWell,
    TightFit,
    TooLarge,
}

How well a model is expected to run given available memory.

Variants

RunsWell

Comfortable — well under the runs-well fraction of memory.

TightFit

Fits, but with little headroom.

TooLarge

Won’t fit comfortably.

Implementations

impl FitVerdict

pub fn as_str(&self) -> &'static str

The stable string form: runs_well, tight_fit, or too_large.

pub fn assess( footprint_mb: Option<i64>, total_memory_bytes: u64, ) -> Option<FitAssessment>

Assess a footprint_mb model against total_memory_bytes. Returns None when the footprint is unknown/non-positive or the memory total is zero.

Trait Implementations

impl Clone for FitVerdict

fn clone(&self) -> FitVerdict

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for FitVerdict

impl Debug for FitVerdict

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

Formats the value using the given formatter.

impl Eq for FitVerdict

impl Hash for FitVerdict

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for FitVerdict

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for FitVerdict