Struct TensorCompress 

pub struct TensorCompress { /* private fields */ }

Tensor compressor with adaptive level selection

Implementations

impl TensorCompress

pub fn new() -> Self

Create a new tensor compressor with default settings

pub fn compress( &self, embedding: &[f32], access_freq: f32, ) -> Result<CompressedTensor>

Compress an embedding based on access frequency

Arguments

• embedding - The input embedding vector
• access_freq - Access frequency in range [0.0, 1.0]

Returns

Compressed tensor using adaptive compression level

pub fn compress_with_level( &self, embedding: &[f32], level: &CompressionLevel, ) -> Result<CompressedTensor>

Compress with explicit compression level

pub fn decompress(&self, compressed: &CompressedTensor) -> Result<Vec<f32>>

Decompress a compressed tensor

Trait Implementations

impl Clone for TensorCompress

fn clone(&self) -> TensorCompress

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TensorCompress

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

Formats the value using the given formatter.

impl Default for TensorCompress

fn default() -> Self

Returns the “default value” for a type.