#[repr(u8)]pub enum DataType {
F32 = 0,
F16 = 1,
BF16 = 2,
I8 = 3,
U8 = 4,
I4 = 5,
Binary = 6,
PQ = 7,
Custom = 8,
}Expand description
Identifies the numeric encoding of vector elements.
Variants§
F32 = 0
32-bit IEEE 754 float.
F16 = 1
16-bit IEEE 754 half-precision float.
BF16 = 2
Brain floating point (bfloat16).
I8 = 3
Signed 8-bit integer (scalar quantized).
U8 = 4
Unsigned 8-bit integer.
I4 = 5
4-bit integer (packed, 2 per byte).
Binary = 6
1-bit binary (packed, 8 per byte).
PQ = 7
Product-quantized codes.
Custom = 8
Custom encoding (see QUANT_SEG for details).
Implementations§
Trait Implementations§
impl Copy for DataType
impl Eq for DataType
impl StructuralPartialEq for DataType
Auto Trait Implementations§
impl Freeze for DataType
impl RefUnwindSafe for DataType
impl Send for DataType
impl Sync for DataType
impl Unpin for DataType
impl UnwindSafe for DataType
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