Skip to main content

BlockQ2K

Struct BlockQ2K 

Source
#[repr(C)]
pub struct BlockQ2K { pub scales: [u8; 16], pub qs: [u8; 64], pub d: f16, pub dmin: f16, }
Expand description

Q2_K super-block: 256 weights quantized to 2 bits each.

Layout (84 bytes):

  • scales: 16 bytes — packed 4-bit scale/min pairs for 16 sub-blocks of 16 weights. Each byte holds two 4-bit values: low nibble = scale, high nibble = min.
  • qs: 64 bytes — 256 x 2-bit quantized weights (4 per byte, LSB first).
  • d: FP16 super-block scale.
  • dmin: FP16 super-block minimum.

Dequant: w[i] = d * sub_scale * q[i] - dmin * sub_min

Fields§

§scales: [u8; 16]

Packed 4-bit scale/min pairs for 16 sub-blocks.

§qs: [u8; 64]

256 x 2-bit quantized weights, 4 per byte.

§d: f16

Super-block scale (FP16).

§dmin: f16

Super-block minimum (FP16).

Implementations§

Source§

impl BlockQ2K

Source

pub fn dequant(blocks: &[Self], output: &mut [f32]) -> BonsaiResult<()>

Dequantize a slice of Q2_K blocks into f32 output.

output must have length blocks.len() * QK_K.

Source

pub fn quantize(input: &[f32]) -> BonsaiResult<Vec<Self>>

Quantize f32 input into Q2_K blocks.

Input length must be a multiple of QK_K (256).

Source

pub fn dequant_row_to_buf(blocks_for_row: &[Self], buf: &mut Vec<f32>)

Dequantize a single row’s worth of Q2_K blocks into a pre-allocated buffer.

buf will be extended by blocks_for_row.len() * 256 elements.

Source

pub fn slice_from_bytes(data: &[u8]) -> BonsaiResult<&[Self]>

Zero-copy cast of a byte slice to a slice of BlockQ2K.

Returns error if length is not a multiple of BLOCK_Q2_K_BYTES (84) or if the pointer is not properly aligned.

Trait Implementations§

Source§

impl Clone for BlockQ2K

Source§

fn clone(&self) -> BlockQ2K

Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Copy for BlockQ2K

Source§

impl Debug for BlockQ2K

Source§

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

Formats the value using the given formatter. Read more
Source§

impl PartialEq for BlockQ2K

Source§

fn eq(&self, other: &BlockQ2K) -> bool

Tests for self and other values to be equal, and is used by ==.
1.0.0 (const: unstable) · Source§

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.
Source§

impl StructuralPartialEq for BlockQ2K

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

Source§

impl<T> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,

Source§

impl<T> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more