pub enum QuantizationConfig {
INT8 {
symmetric: bool,
},
INT4 {
group_size: usize,
},
FP8 {
e4m3: bool,
},
GPTQ {
bits: u8,
group_size: usize,
desc_act: bool,
},
AWQ {
bits: u8,
zero_point: bool,
},
}Expand description
Quantization configuration for weights
Variants§
INT8
INT8 uniform quantization
INT4
INT4 grouped quantization
FP8
FP8 quantization
GPTQ
GPTQ quantization
AWQ
AWQ quantization
Trait Implementations§
Source§impl Clone for QuantizationConfig
impl Clone for QuantizationConfig
Source§fn clone(&self) -> QuantizationConfig
fn clone(&self) -> QuantizationConfig
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 QuantizationConfig
impl Debug for QuantizationConfig
Source§impl<'de> Deserialize<'de> for QuantizationConfig
impl<'de> Deserialize<'de> for QuantizationConfig
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 QuantizationConfig
impl RefUnwindSafe for QuantizationConfig
impl Send for QuantizationConfig
impl Sync for QuantizationConfig
impl Unpin for QuantizationConfig
impl UnsafeUnpin for QuantizationConfig
impl UnwindSafe for QuantizationConfig
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