pub enum QuantMethod {
None,
Gptq,
Awq,
Gguf,
}Expand description
The quantization scheme in use, if any.
Variants§
None
No quantization — dense fp32/fp16/bf16 weights.
Gptq
GPTQ: int4/int8 group-wise with scales + zeros, asymmetric.
Awq
AWQ: int4 group-wise, similar to GPTQ but different packing.
Gguf
GGUF: k-quants and legacy quants embedded in a single-file format.
Trait Implementations§
Source§impl Clone for QuantMethod
impl Clone for QuantMethod
Source§fn clone(&self) -> QuantMethod
fn clone(&self) -> QuantMethod
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 QuantMethod
impl Debug for QuantMethod
Source§impl Default for QuantMethod
impl Default for QuantMethod
Source§impl<'de> Deserialize<'de> for QuantMethod
impl<'de> Deserialize<'de> for QuantMethod
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
Source§impl PartialEq for QuantMethod
impl PartialEq for QuantMethod
Source§impl Serialize for QuantMethod
impl Serialize for QuantMethod
impl Eq for QuantMethod
impl StructuralPartialEq for QuantMethod
Auto Trait Implementations§
impl Freeze for QuantMethod
impl RefUnwindSafe for QuantMethod
impl Send for QuantMethod
impl Sync for QuantMethod
impl Unpin for QuantMethod
impl UnsafeUnpin for QuantMethod
impl UnwindSafe for QuantMethod
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