llama_model_quantize_params class final
model quantization parameters
- Inheritance
- Implemented types
- Available extensions
Constructors
Properties
- allow_requantize ↔ bool
-
allow quantizing non-f32/f16 tensors
getter/setter pair
- ftype ↔ int
-
quantize to this llama_ftype
getter/setter pair
- hashCode → int
-
The hash code for this object.
no setterinherited
- nthread ↔ int
-
number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
getter/setter pair
- only_copy ↔ bool
-
only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
getter/setter pair
- pure ↔ bool
-
disable k-quant mixtures and quantize all tensors to the same type
getter/setter pair
- quantize_output_tensor ↔ bool
-
quantize output.weight
getter/setter pair
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited