pub struct QuantizedTensor {
pub data: Vec<f32>,
pub scales: Vec<f32>,
pub zero_points: Vec<f32>,
pub shape: Vec<usize>,
pub method: QuantizationMethod,
pub block_size: usize,
}Expand description
Quantized tensor representation (simplified version)
Fields§
§data: Vec<f32>Quantized data (simplified as f32 for compatibility)
scales: Vec<f32>Scale factors for dequantization
zero_points: Vec<f32>Zero points for asymmetric quantization
shape: Vec<usize>Original tensor shape
method: QuantizationMethodQuantization method used
block_size: usizeBlock size (for block-wise quantization)
Implementations§
Source§impl QuantizedTensor
impl QuantizedTensor
Sourcepub fn new(
data: Vec<f32>,
scales: Vec<f32>,
zero_points: Vec<f32>,
shape: Vec<usize>,
method: QuantizationMethod,
block_size: usize,
) -> Self
pub fn new( data: Vec<f32>, scales: Vec<f32>, zero_points: Vec<f32>, shape: Vec<usize>, method: QuantizationMethod, block_size: usize, ) -> Self
Create a new quantized tensor
Sourcepub fn memory_usage(&self) -> usize
pub fn memory_usage(&self) -> usize
Get memory usage in bytes (simplified)
Sourcepub fn compression_ratio(&self) -> f32
pub fn compression_ratio(&self) -> f32
Get compression ratio compared to full precision (theoretical for 4-bit)
Trait Implementations§
Source§impl Clone for QuantizedTensor
impl Clone for QuantizedTensor
Source§fn clone(&self) -> QuantizedTensor
fn clone(&self) -> QuantizedTensor
Returns a duplicate of the value. Read more
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for QuantizedTensor
impl Debug for QuantizedTensor
Source§impl<'de> Deserialize<'de> for QuantizedTensor
impl<'de> Deserialize<'de> for QuantizedTensor
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
Auto Trait Implementations§
impl Freeze for QuantizedTensor
impl RefUnwindSafe for QuantizedTensor
impl Send for QuantizedTensor
impl Sync for QuantizedTensor
impl Unpin for QuantizedTensor
impl UnwindSafe for QuantizedTensor
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<T> ConfigSerializable for Twhere
T: Serialize + for<'de> Deserialize<'de>,
impl<T> ConfigSerializable for Twhere
T: Serialize + for<'de> Deserialize<'de>,
Source§fn save_to_file(&self, path: &Path) -> Result<(), TrustformersError>
fn save_to_file(&self, path: &Path) -> Result<(), TrustformersError>
Save to file
Source§fn load_from_file(path: &Path) -> Result<Self, TrustformersError>where
Self: Sized,
fn load_from_file(path: &Path) -> Result<Self, TrustformersError>where
Self: Sized,
Load from file
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
Source§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
fn into_either(self, into_left: bool) -> Either<Self, Self>
Converts
self into a Left variant of Either<Self, Self>
if into_left is true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
Converts
self into a Left variant of Either<Self, Self>
if into_left(&self) returns true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read more