Enum CpuCompressionMethod 

pub enum CpuCompressionMethod {
    None,
    FP16,
    BF16,
    INT8,
    Quantization,
    LosslessCompression,
}

Compression methods for CPU-stored data

Variants

None

No compression

FP16

16-bit floating point compression

BF16

BFloat16 compression

INT8

8-bit integer quantization

Quantization

Advanced quantization schemes

LosslessCompression

Lossless compression (e.g., LZ4, Snappy)

Implementations

impl CpuCompressionMethod

pub fn ratio(&self) -> f32

Get the compression ratio (0.0 to 1.0, where 1.0 means no compression)

pub fn is_lossy(&self) -> bool

Check if this compression method is lossy

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

Get a human-readable description

Trait Implementations

impl Clone for CpuCompressionMethod

fn clone(&self) -> CpuCompressionMethod

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CpuCompressionMethod

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

Formats the value using the given formatter.

impl PartialEq for CpuCompressionMethod

fn eq(&self, other: &CpuCompressionMethod) -> 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 CpuCompressionMethod

impl Eq for CpuCompressionMethod

impl StructuralPartialEq for CpuCompressionMethod